© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 12288
    Prev
    Next
    INDEX
    Explanations

    mentions of a character named Dro being taken out or dropping items with varying intensities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    659
    +0.09
    0.6%
    569
    +0.07
    0.5%
    409
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.09
    0.06
    659
    +0.07
    0.05
    288
    +0.07
    0.07
    Negative Logits
     Canary
    -0.52
     @@
    -0.50
     Caldwell
    -0.47
     Appalachian
    -0.47
    é¾įåĸļ士
    -0.46
     Divide
    -0.46
     americ
    -0.45
     IST
    -0.45
     mant
    -0.44
    sburgh
    -0.44
    POSITIVE LOGITS
    plets
    0.64
     Dro
    0.63
    ogle
    0.62
    bage
    0.61
    phant
    0.59
    opa
    0.59
    cffff
    0.58
    rolet
    0.57
    bed
    0.57
    bing
    0.57
    Activations Density 0.673%

    No Known Activations