© 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 EvalsExportsinterp-engineNEWAPI 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. 32352
    Prev
    Next
    INDEX
    Explanations

    information related to educational achievements and graduations

    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
    557
    +0.09
    0.6%
    6
    +0.07
    0.5%
    312
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.09
    0.17
    362
    +0.07
    0.12
    608
    +0.07
    0.15
    Negative Logits
    eele
    -0.55
    isphere
    -0.54
    ItemThumbnailImage
    -0.52
    witch
    -0.51
    zsche
    -0.51
     excuse
    -0.51
    ilver
    -0.50
    seek
    -0.48
    skinned
    -0.48
    agy
    -0.47
    POSITIVE LOGITS
     Sta
    0.57
     Pett
    0.52
     Parsons
    0.52
     Corpus
    0.51
     Tucson
    0.50
     Tree
    0.48
    ature
    0.48
     Zurich
    0.48
     Buc
    0.48
     Berk
    0.48
    Activations Density 6.592%

    No Known Activations