© 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. 12905
    Prev
    Next
    INDEX
    Explanations

    names of people or locations

    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
    573
    +0.10
    0.6%
    494
    +0.09
    0.5%
    467
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.10
    0.14
    640
    +0.09
    0.21
    486
    +0.08
    0.02
    Negative Logits
     craw
    -0.59
    uyomi
    -0.58
    phrine
    -0.57
    ħĭ
    -0.56
    ãĤ´ãĥ³
    -0.56
     fung
    -0.56
     fluor
    -0.54
    bley
    -0.54
    plings
    -0.54
     wax
    -0.54
    POSITIVE LOGITS
    uay
    0.86
    eta
    0.79
    ultural
    0.79
    andise
    0.73
    ement
    0.69
    ulture
    0.69
    illas
    0.68
    Plot
    0.66
    emia
    0.65
    iru
    0.65
    Activations Density 10.446%

    No Known Activations