© 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. 33762
    Prev
    Next
    INDEX
    Explanations

    verbs related to denial, acknowledgement, and resistance in text

    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
    234
    +0.08
    0.5%
    218
    +0.07
    0.5%
    108
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    108
    +0.08
    0.09
    608
    +0.07
    0.17
    589
    +0.07
    0.07
    Negative Logits
    blogspot
    -0.52
    gow
    -0.50
    chie
    -0.49
    emies
    -0.49
    ighth
    -0.48
    ummies
    -0.47
    zbek
    -0.47
    onies
    -0.46
    itched
    -0.45
    ollah
    -0.45
    POSITIVE LOGITS
     temptation
    0.64
    FontSize
    0.50
    >)
    0.50
     anymore
    0.49
     anything
    0.47
     nor
    0.45
     them
    0.45
    ANCE
    0.44
     anybody
    0.44
    ned
    0.43
    Activations Density 12.232%

    No Known Activations