© 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
    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. 1513
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Adventure."

    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
    288
    +0.21
    0.9%
    549
    +0.18
    0.8%
    183
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.21
    0.11
    326
    +0.18
    0.08
    549
    +0.14
    0.05
    Negative Logits
    heed
    -0.98
    iets
    -0.96
    creen
    -0.93
    iths
    -0.89
    enser
    -0.88
    animous
    -0.87
    aves
    -0.80
    xual
    -0.80
    aps
    -0.78
    ipp
    -0.77
    POSITIVE LOGITS
    nels
    0.88
     Grande
    0.83
    Adventure
    0.80
     Reborn
    0.77
     Werewolf
    0.77
     Mouse
    0.76
     Luffy
    0.76
     Adventures
    0.75
     Phant
    0.74
     Riders
    0.74
    Activations Density 1.027%

    No Known Activations