© 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. 40342
    Prev
    Next
    INDEX
    Explanations

    content related to political events and opinions

    oai_token-act-pair · gpt-3.5-turbo

    words that are numerically quantified or associated with numerical values

    oai_token-act-pair · gpt-3.5-turboTriggered by @jordan
    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
    1.6%
    29
    +0.09
    0.5%
    617
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.26
    0.04
    727
    +0.09
    0.08
    195
    +0.07
    -0.02
    Negative Logits
    ãĤ´ãĥ³
    -0.50
     Antar
    -0.50
     reins
    -0.49
     behav
    -0.46
     suscept
    -0.44
    ãĥ³ãĤ¸
    -0.44
    ãĤĬ
    -0.44
     respectively
    -0.43
     Hades
    -0.43
     derby
    -0.42
    POSITIVE LOGITS
    [/
    0.70
     [/
    0.65
     [+
    0.64
    wcsstore
    0.63
     [
    0.60
    orem
    0.60
     guiName
    0.56
    reetings
    0.54
     [*
    0.52
     [âĢ¦]
    0.52
    Activations Density 13.029%

    No Known Activations