© 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. 40414
    Prev
    Next
    INDEX
    Explanations

    discussion related to political and administrative topics

    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
    +0.29
    1.6%
    36
    +0.17
    0.9%
    393
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.29
    0.39
    250
    +0.17
    0.11
    393
    +0.16
    0.28
    Negative Logits
     Jagu
    -0.61
     Adin
    -0.54
    arsity
    -0.53
     âĢķ
    -0.52
     Atkins
    -0.52
    ":[
    -0.51
    evidence
    -0.51
    AIDS
    -0.51
     GMOs
    -0.51
    Finish
    -0.50
    POSITIVE LOGITS
    cknowled
    1.27
    cknow
    1.07
    verages
    1.03
    UTH
    0.94
    gency
    0.93
    chieve
    0.91
    usterity
    0.89
    ircraft
    0.88
     spokesperson
    0.86
    lyss
    0.85
    Activations Density 12.302%

    No Known Activations