© 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. 11494
    Prev
    Next
    INDEX
    Explanations

    references to fishing targets and fishing-related activities

    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
    447
    +0.17
    0.6%
    543
    +0.16
    0.6%
    124
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    93
    +0.17
    0.04
    326
    +0.16
    0.07
    336
    +0.13
    0.04
    Negative Logits
     diabetic
    -0.90
    cffff
    -0.83
     Constantine
    -0.83
    doi
    -0.80
    785
    -0.77
     reconc
    -0.77
    iesel
    -0.76
    nen
    -0.75
    owed
    -0.75
    485
    -0.75
    POSITIVE LOGITS
    Info
    0.95
    OTAL
    0.90
     Weekly
    0.88
     Gren
    0.85
    Sounds
    0.85
    Manager
    0.85
     Wraith
    0.84
    Tips
    0.83
    aneers
    0.83
    eers
    0.82
    Activations Density 0.763%

    No Known Activations