© 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. 40541
    Prev
    Next
    INDEX
    Explanations

    web URLs

    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
    443
    +0.06
    0.5%
    440
    +0.06
    0.5%
    373
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.06
    -0.11
    231
    +0.06
    0.05
    696
    +0.05
    0.07
    Negative Logits
     UNCLASSIFIED
    -0.53
    andum
    -0.45
    forth
    -0.42
    endix
    -0.39
    cussion
    -0.38
    Newsletter
    -0.38
    apixel
    -0.37
    adier
    -0.36
    lihood
    -0.36
    ruary
    -0.36
    POSITIVE LOGITS
    tv
    0.35
    Rated
    0.34
    onto
    0.34
     attraction
    0.34
     cruising
    0.32
     retro
    0.32
     attractions
    0.32
    anners
    0.31
     homeowner
    0.31
    Els
    0.31
    Activations Density 3.242%

    No Known Activations