© 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. 32686
    Prev
    Next
    INDEX
    Explanations

    French phrases related to exploration or discovery

    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
    389
    +0.14
    0.6%
    445
    +0.12
    0.5%
    316
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.14
    0.06
    216
    +0.12
    0.07
    471
    +0.12
    0.06
    Negative Logits
    DAY
    -0.87
    regor
    -0.86
    OWS
    -0.80
    Reviewer
    -0.75
    enhagen
    -0.71
    ancial
    -0.71
    STER
    -0.70
    glers
    -0.70
     Holmes
    -0.69
    regon
    -0.68
    POSITIVE LOGITS
    ugar
    0.93
    erve
    0.88
    ync
    0.82
    erves
    0.82
    cipl
    0.82
    plet
    0.82
    aturated
    0.81
    icc
    0.80
    cend
    0.80
    ynchron
    0.79
    Activations Density 6.361%

    No Known Activations