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

    Neuronpedia

    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. 39599
    Prev
    Next
    INDEX
    Explanations

    actions or events that are imposed on someone or a group, often against their will, or involving a difficult or challenging situation

    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
    +0.31
    1.4%
    665
    +0.13
    0.6%
    393
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.31
    0.20
    665
    +0.13
    0.19
    393
    +0.12
    0.24
    Negative Logits
    laughter
    -0.77
    calling
    -0.73
    anooga
    -0.69
    ergy
    -0.68
     Prediction
    -0.65
     Blueprint
    -0.63
    fortunately
    -0.62
    cli
    -0.62
     Compass
    -0.61
     Majority
    -0.60
    POSITIVE LOGITS
     endure
    1.18
     confront
    1.11
     reckon
    1.08
     undergo
    1.07
     obey
    1.02
     fend
    1.01
     undertake
    1.01
     abandon
    1.00
     reconsider
    0.99
     rethink
    0.98
    Activations Density 9.264%

    No Known Activations