© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 36513
    Prev
    Next
    INDEX
    Explanations

    terms related to Guantanamo Bay detention, including mentions of specific conditions, actions, and locations related to the facility

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.10
    0.6%
    175
    +0.08
    0.5%
    325
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.10
    0.26
    442
    +0.08
    0.13
    160
    +0.08
    0.20
    Negative Logits
     Franch
    -0.69
    Merit
    -0.64
    WN
    -0.56
    idas
    -0.55
     Shelley
    -0.53
     Jord
    -0.53
     Pixie
    -0.52
     ancest
    -0.52
    iosyncr
    -0.52
    iren
    -0.52
    POSITIVE LOGITS
    anamo
    0.87
     Guantanamo
    0.81
     detainees
    0.77
     detention
    0.73
     detainee
    0.71
     Hussein
    0.70
     Guant
    0.70
    adr
    0.62
    ilitation
    0.61
    atari
    0.61
    Activations Density 8.270%

    No Known Activations