© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 2289
    Prev
    Next
    INDEX
    Explanations

    references to individuals or characters in a storyline, possibly from the entertainment industry

    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
    240
    +0.20
    0.6%
    326
    +0.17
    0.6%
    178
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.20
    0.04
    326
    +0.17
    0.05
    494
    +0.15
    0.04
    Negative Logits
     destro
    -1.10
    女
    -1.06
     Luxem
    -1.02
    HCR
    -1.01
     contracted
    -0.98
    士
    -0.98
    minist
    -0.96
     confir
    -0.96
     rall
    -0.95
    rehens
    -0.94
    POSITIVE LOGITS
     prest
    1.42
     hey
    1.42
    hey
    1.27
    tons
    1.20
    terson
    1.18
    oka
    1.14
    bye
    1.12
     guys
    1.11
    giving
    1.11
     pardon
    1.00
    Activations Density 0.776%

    No Known Activations