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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 100
    Prev
    Next
    INDEX
    Explanations

    references to vocalists and vocals in various contexts such as music and public criticism

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    •Two-Channel: Scaffold vs Backbone Features (GPT-2)

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    99
    +0.20
    0.7%
    288
    +0.17
    0.6%
    167
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.20
    0.08
    99
    +0.17
    0.06
    151
    +0.13
    0.06
    Negative Logits
     Reincarn
    -1.07
    uden
    -0.99
    IDA
    -0.86
     Cunningham
    -0.85
     Drawn
    -0.84
    ionage
    -0.84
     Soldiers
    -0.81
     Peb
    -0.81
    ILD
    -0.80
     Profit
    -0.80
    POSITIVE LOGITS
     cords
    1.44
     chords
    1.42
    izations
    1.27
    isations
    1.24
    acters
    1.12
    izes
    1.07
     fry
    1.07
    izer
    1.06
    unci
    1.06
     vocal
    1.04
    Activations Density 0.979%

    No Known Activations