© 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. 32691
    Prev
    Next
    INDEX
    Explanations

    proper names

    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
    288
    +0.12
    0.6%
    167
    +0.11
    0.5%
    286
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.18
    68
    +0.11
    0.05
    153
    +0.10
    0.07
    Negative Logits
    xual
    -0.72
    BOOK
    -0.69
     ãĤµ
    -0.60
    LY
    -0.59
     malfunction
    -0.59
    VALUE
    -0.58
    anwhile
    -0.58
    versible
    -0.58
    ension
    -0.58
    ishops
    -0.58
    POSITIVE LOGITS
    igan
    1.20
    iard
    1.09
    iland
    1.08
    igans
    1.04
    iants
    1.01
    iage
    0.99
    wyn
    0.95
    espie
    0.92
    ies
    0.88
    iant
    0.88
    Activations Density 6.640%

    No Known Activations