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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 33162
    Prev
    Next
    INDEX
    Explanations

    words related to physical barriers or confinement, such as cages and shackles

    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
    549
    +0.13
    0.6%
    710
    +0.11
    0.5%
    585
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.23
    288
    +0.11
    0.23
    25
    +0.10
    0.07
    Negative Logits
    uary
    -0.73
    inates
    -0.68
    atio
    -0.67
    én
    -0.66
    axy
    -0.66
    enhagen
    -0.64
    ingham
    -0.63
    enthal
    -0.63
    inating
    -0.63
    estate
    -0.62
    POSITIVE LOGITS
     confinement
    0.92
     shack
    0.86
     bred
    0.81
     cages
    0.79
    hold
    0.79
     cage
    0.75
    hered
    0.74
    doors
    0.69
    âķ
    0.66
     Horses
    0.66
    Activations Density 8.437%

    No Known Activations