© 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. 32488
    Prev
    Next
    INDEX
    Explanations

    references to various types of paper or paper-related activities

    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%
    167
    +0.13
    0.6%
    213
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.23
    -0.04
    683
    +0.13
    0.09
    371
    +0.13
    0.10
    Negative Logits
    cffffcc
    -0.89
    ivals
    -0.77
    oise
    -0.73
    Ģ
    -0.73
    cffff
    -0.72
     ambassadors
    -0.71
    igious
    -0.71
    inia
    -0.71
    ostic
    -0.70
    essee
    -0.68
    POSITIVE LOGITS
    clip
    1.39
     towels
    1.20
    clips
    1.06
    backs
    1.02
     towel
    0.98
     pus
    0.95
    thin
    0.90
    maid
    0.90
    weight
    0.87
    bag
    0.86
    Activations Density 7.242%

    No Known Activations