© 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. 35986
    Prev
    Next
    INDEX
    Explanations

    actions related to caring and teaching, especially in the context of wilderness skills and quality time spent with children

    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
    +0.28
    1.1%
    621
    +0.15
    0.6%
    474
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    119
    +0.28
    0.16
    750
    +0.15
    0.09
    351
    +0.12
    0.07
    Negative Logits
    vious
    -0.78
     Cavaliers
    -0.76
     Nile
    -0.76
     optionally
    -0.74
     rightfully
    -0.74
    anwhile
    -0.73
     admittedly
    -0.73
    assi
    -0.72
     Sisters
    -0.71
    viously
    -0.70
    POSITIVE LOGITS
    ĨĴ
    0.89
    Buff
    0.82
    aeda
    0.80
    illon
    0.79
     shit
    0.75
    govtrack
    0.73
    PsyNetMessage
    0.73
     Hoff
    0.73
    hig
    0.73
    ench
    0.72
    Activations Density 17.304%

    No Known Activations