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

    Neuronpedia

    Jacobian LensNEW
    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. 33424
    Prev
    Next
    INDEX
    Explanations

    wishes of well-being and success for individuals

    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
    105
    +0.11
    0.6%
    220
    +0.07
    0.4%
    567
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.11
    0.28
    446
    +0.07
    0.10
    567
    +0.07
    0.08
    Negative Logits
     Cosponsors
    -0.73
    anto
    -0.65
    ngth
    -0.63
     sidx
    -0.56
    catentry
    -0.55
    ethy
    -0.53
    furt
    -0.52
    esm
    -0.52
    ongh
    -0.52
    atech
    -0.50
    POSITIVE LOGITS
     farewell
    0.65
     luck
    0.65
    present
    0.57
     blessings
    0.56
     afterlife
    0.56
     blessed
    0.55
    Appearances
    0.55
     forgiveness
    0.54
    thood
    0.54
    Forward
    0.53
    Activations Density 13.143%

    No Known Activations