© 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. 33165
    Prev
    Next
    INDEX
    Explanations

    words related to objections and opposing viewpoints

    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
    +0.23
    1.0%
    679
    +0.15
    0.6%
    496
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    705
    +0.23
    0.10
    52
    +0.15
    0.08
    709
    +0.11
    0.09
    Negative Logits
     Tycoon
    -0.85
    negie
    -0.82
    ifter
    -0.78
     ILCS
    -0.78
    estones
    -0.78
    mberg
    -0.76
     Loaded
    -0.76
    oufl
    -0.73
    oiler
    -0.69
    estone
    -0.68
    POSITIVE LOGITS
     thereto
    1.05
     vehemently
    0.86
    naires
    0.86
     stren
    0.80
    ¿½
    0.77
     against
    0.71
     vigorously
    0.70
     objections
    0.68
    onent
    0.67
     disbel
    0.67
    Activations Density 6.752%

    No Known Activations