© 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 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. 6485
    Prev
    Next
    INDEX
    Explanations

    management-related information like press releases, financial statements, and business announcements

    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
    +0.23
    0.8%
    497
    +0.14
    0.5%
    640
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.23
    0.22
    679
    +0.14
    0.23
    640
    +0.12
    0.22
    Negative Logits
    roman
    -0.96
     cryst
    -0.91
     reckon
    -0.87
     botched
    -0.86
     creeps
    -0.84
     swapped
    -0.84
     creep
    -0.83
     guessed
    -0.83
    unts
    -0.83
     glob
    -0.82
    POSITIVE LOGITS
    Abstract
    1.26
    Summary
    1.05
    ¶
    1.04
    doi
    1.03
    Supplement
    1.02
    Study
    0.98
    Introduction
    0.96
     Introduction
    0.96
    ospons
    0.94
    Experience
    0.94
    Activations Density 5.169%

    No Known Activations