© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 37114
    Prev
    Next
    INDEX
    Explanations

    references to fictional tales or stories

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.12
    0.8%
    235
    +0.11
    0.7%
    549
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    235
    +0.12
    0.12
    444
    +0.11
    0.07
    1
    +0.10
    0.08
    Negative Logits
    erate
    -0.65
    ividual
    -0.58
    ulty
    -0.57
    atever
    -0.57
    apsed
    -0.56
    ervatives
    -0.54
    eele
    -0.53
    bledon
    -0.52
    itates
    -0.51
    ierrez
    -0.51
    POSITIVE LOGITS
     tales
    0.79
    tale
    0.74
     tale
    0.74
     Tale
    0.69
     Reincarn
    0.69
     Tales
    0.68
    tell
    0.65
    ttes
    0.63
    é¾įåĸļ士
    0.55
     Witches
    0.53
    Activations Density 8.343%

    No Known Activations