© 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. 36181
    Prev
    Next
    INDEX
    Explanations

    mentions of retired individuals with different ranks and positions, particularly in the military and law enforcement

    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
    447
    +0.24
    1.0%
    288
    +0.19
    0.8%
    27
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.24
    0.31
    43
    +0.19
    0.11
    442
    +0.10
    0.10
    Negative Logits
    iola
    -0.82
    owitz
    -0.74
     Grimm
    -0.73
    otion
    -0.70
    matic
    -0.68
    ella
    -0.68
    amus
    -0.67
     Hispan
    -0.66
    ebus
    -0.66
     Rig
    -0.66
    POSITIVE LOGITS
     retiring
    0.84
    dinand
    0.79
     retire
    0.78
    oslov
    0.74
    spective
    0.74
     accountant
    0.70
    avorite
    0.70
    Veter
    0.69
     pensions
    0.68
    ret
    0.67
    Activations Density 9.882%

    No Known Activations