© 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. 33781
    Prev
    Next
    INDEX
    Explanations

    mentions of expertise, mastery, or highly skilled individuals in various contexts

    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
    +0.19
    0.8%
    59
    +0.15
    0.6%
    167
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.19
    0.25
    160
    +0.15
    0.18
    522
    +0.14
    0.10
    Negative Logits
    OPLE
    -0.94
    IDER
    -0.75
    ople
    -0.74
    enegger
    -0.73
     Strip
    -0.73
    DEN
    -0.72
     Aren
    -0.70
     retirees
    -0.70
    AAF
    -0.70
    hedon
    -0.69
    POSITIVE LOGITS
    pieces
    1.56
    mind
    1.31
    piece
    1.27
    class
    1.11
    stroke
    1.10
    fully
    1.03
    sonian
    1.03
    classes
    1.01
    work
    1.00
    ful
    0.97
    Activations Density 12.216%

    No Known Activations