© 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. 45900
    Prev
    Next
    INDEX
    Explanations

    phrases related to questioning, politics, statistics, and social issues

    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
    +0.11
    0.7%
    49
    +0.08
    0.5%
    196
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.11
    0.41
    6
    +0.08
    0.22
    64
    +0.08
    -0.29
    Negative Logits
    azel
    -0.56
     wary
    -0.53
     aval
    -0.52
     ensued
    -0.52
     nearby
    -0.51
     symp
    -0.49
     detected
    -0.48
     unmarked
    -0.48
     hesitant
    -0.47
     authorised
    -0.47
    POSITIVE LOGITS
     namely
    0.81
    WIN
    0.54
    ENGTH
    0.53
    âĹı
    0.53
    IENCE
    0.52
    DEF
    0.51
    HOW
    0.50
    INS
    0.49
    _____
    0.49
    DON
    0.49
    Activations Density 17.006%

    No Known Activations