© 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. 33651
    Prev
    Next
    INDEX
    Explanations

    written responses or interactions thanking someone or acknowledging support

    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
    379
    +0.12
    0.5%
    604
    +0.10
    0.5%
    362
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.12
    0.24
    159
    +0.10
    0.09
    566
    +0.10
    0.09
    Negative Logits
    soever
    -0.85
    ħĭ
    -0.79
    ¶ħ
    -0.77
    etheless
    -0.76
    everal
    -0.74
    aults
    -0.74
    tle
    -0.73
    ntil
    -0.72
    paio
    -0.72
    ofi
    -0.71
    POSITIVE LOGITS
     inconvenience
    0.88
     pains
    0.71
     submission
    0.70
     contribution
    0.69
     kindly
    0.69
     generosity
    0.68
     patronage
    0.67
     contributions
    0.66
     patience
    0.66
     advances
    0.65
    Activations Density 10.852%

    No Known Activations