© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 34973
    Prev
    Next
    INDEX
    Explanations

    past tense verbs related to personal experiences or actions

    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
    +0.26
    1.4%
    339
    +0.11
    0.6%
    328
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    328
    +0.26
    0.05
    290
    +0.11
    0.09
    339
    +0.11
    0.07
    Negative Logits
     Canaver
    -0.64
    oute
    -0.56
    aminer
    -0.56
     Gould
    -0.54
     Rodrigo
    -0.54
    Sup
    -0.54
     Vish
    -0.52
     Brah
    -0.51
     srfAttach
    -0.51
    retched
    -0.50
    POSITIVE LOGITS
     responders
    0.89
     baseman
    0.88
     glance
    0.81
     blush
    0.81
     lady
    0.70
     conceived
    0.69
    born
    0.63
     appeared
    0.63
     sight
    0.62
     glim
    0.62
    Activations Density 9.546%

    No Known Activations