© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 33994
    Prev
    Next
    INDEX
    Explanations

    statements indicating personal opinion or intention

    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
    0.9%
    107
    +0.10
    0.6%
    95
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    661
    +0.15
    0.07
    697
    +0.10
    0.07
    95
    +0.07
    0.06
    Negative Logits
     Hebdo
    -0.47
    Reviewer
    -0.46
    taboola
    -0.46
     rab
    -0.46
     Scores
    -0.43
    itles
    -0.43
    endez
    -0.43
     scree
    -0.42
    lation
    -0.41
    rawdownloadcloneembedreportprint
    -0.41
    POSITIVE LOGITS
     myself
    0.67
    é¾įå
    0.58
    ishi
    0.56
    ĸļ
    0.54
     personally
    0.53
    cious
    0.52
    ¿½
    0.50
    na
    0.50
    igo
    0.49
     fortunate
    0.48
    Activations Density 5.337%

    No Known Activations