© 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. 45807
    Prev
    Next
    INDEX
    Explanations

    mentions or descriptions of code comments or explanations

    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
    +0.07
    0.5%
    646
    +0.07
    0.5%
    223
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    711
    +0.07
    0.04
    255
    +0.07
    0.13
    756
    +0.06
    -0.23
    Negative Logits
     Limbaugh
    -0.51
    ournal
    -0.48
    ista
    -0.47
    ophobia
    -0.43
    ocaust
    -0.42
     handic
    -0.42
    anca
    -0.42
    isma
    -0.42
    istas
    -0.41
     athlet
    -0.41
    POSITIVE LOGITS
     nodes
    0.53
     nested
    0.51
    heses
    0.50
    hesis
    0.49
    layer
    0.45
     node
    0.44
     rows
    0.43
     modules
    0.43
     Node
    0.42
     layer
    0.42
    Activations Density 19.656%

    No Known Activations