© 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 EvalsExportsAPI 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. 33338
    Prev
    Next
    INDEX
    Explanations

    mentions of specific terrorist groups like al-Qaeda or specific militant activities like bombings and attacks

    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
    640
    +0.17
    0.7%
    447
    +0.12
    0.5%
    152
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.17
    0.35
    745
    +0.12
    -0.10
    160
    +0.12
    0.20
    Negative Logits
    wcs
    -0.88
    OPLE
    -0.80
    avorite
    -0.79
     Dickinson
    -0.77
    nesday
    -0.76
    umbnails
    -0.74
     Cosponsors
    -0.73
    rers
    -0.73
    retty
    -0.73
    mble
    -0.71
    POSITIVE LOGITS
    Qaeda
    1.35
    Qaida
    1.30
    bay
    1.10
    Bay
    1.07
    tra
    1.03
    way
    1.00
    su
    0.99
    armed
    0.99
    cont
    0.94
    Lat
    0.94
    Activations Density 10.214%

    No Known Activations