© 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. 4172
    Prev
    Next
    INDEX
    Explanations

    mentions of legal consequences, personal accusations, criminal offenses, investigations, and official statements

    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
    +0.15
    0.8%
    393
    +0.14
    0.7%
    611
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.15
    0.28
    393
    +0.14
    0.26
    669
    +0.10
    0.12
    Negative Logits
    tera
    -0.59
    bet
    -0.58
    earchers
    -0.58
    eele
    -0.57
    ocating
    -0.55
    igmatic
    -0.54
     preval
    -0.54
     ancest
    -0.53
     istg
    -0.53
     exodus
    -0.53
    POSITIVE LOGITS
    ãĤ¦
    0.66
    ESSION
    0.64
    ãĥĺ
    0.59
    tnc
    0.59
     sorts
    0.57
    ãĥīãĥ©
    0.56
    Ö¼
    0.55
    ãĤ¸
    0.55
    ãĥ¼
    0.54
    ãĥ¤
    0.54
    Activations Density 10.540%

    No Known Activations