© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 40654
    Prev
    Next
    INDEX
    Explanations

    JavaScript code snippets

    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
    0.9%
    326
    +0.11
    0.5%
    363
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    564
    +0.19
    0.10
    319
    +0.11
    0.09
    556
    +0.10
    0.09
    Negative Logits
     Tenth
    -0.72
     Harmon
    -0.69
     Ames
    -0.66
     Cris
    -0.65
     confir
    -0.65
     Friendship
    -0.65
     Reincarn
    -0.65
     Skydragon
    -0.64
     Lot
    -0.63
     Hed
    -0.62
    POSITIVE LOGITS
    _
    1.18
    utils
    0.93
    oidal
    0.90
    @
    0.84
    cli
    0.78
     @@
    0.76
    ensis
    0.75
    ragon
    0.74
     +=
    0.74
    rc
    0.74
    Activations Density 9.150%

    No Known Activations