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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 32418
    Prev
    Next
    INDEX
    Explanations

    phrases related to wisdom and wise decision-making

    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
    +0.16
    0.7%
    618
    +0.14
    0.6%
    450
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    450
    +0.16
    0.08
    307
    +0.14
    0.07
    311
    +0.11
    -0.04
    Negative Logits
    alogue
    -0.72
    hedral
    -0.70
     genders
    -0.69
     Gutenberg
    -0.68
     Independence
    -0.64
     shale
    -0.64
    riages
    -0.64
    orescent
    -0.62
    ainers
    -0.61
    ILA
    -0.61
    POSITIVE LOGITS
    guy
    0.92
     counsel
    0.85
    eyed
    0.84
     Advice
    0.84
     advice
    0.79
    comm
    0.79
    man
    0.78
    sa
    0.72
    lings
    0.72
    ness
    0.72
    Activations Density 7.627%

    No Known Activations