© 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. 13022
    Prev
    Next
    INDEX
    Explanations

    narrative elements or storytelling elements in the text

    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
    •Layer 6 UMAP region: Mostly-local line at bottom - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.13
    1.2%
    756
    +0.09
    0.8%
    459
    +0.09
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.37
    575
    +0.09
    0.29
    459
    +0.09
    0.27
    Negative Logits
    ãĤ³
    -0.29
     Sexy
    -0.29
    Pitt
    -0.28
    ãĤµ
    -0.27
    ston
    -0.26
    ãĥ£
    -0.26
     guiActiveUn
    -0.25
    Ball
    -0.25
    edin
    -0.25
    bold
    -0.25
    POSITIVE LOGITS
    ,,,,
    0.43
    .
    0.38
     altogether
    0.35
    eers
    0.34
     wherever
    0.33
     whilst
    0.33
    .","
    0.33
    ;
    0.33
     nonetheless
    0.33
     whereas
    0.32
    Activations Density 13.454%

    No Known Activations