© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10422
    Prev
    Next
    INDEX
    Explanations

    content related to business processes, including templates, financial responsibilities, and employee engagement

    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
    640
    +0.36
    1.2%
    604
    +0.16
    0.6%
    447
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.36
    0.14
    160
    +0.16
    0.10
    6
    +0.14
    0.08
    Negative Logits
     Wander
    -0.90
     nowhere
    -0.86
    quist
    -0.86
    sburgh
    -0.86
     sailed
    -0.85
    heet
    -0.85
    paio
    -0.84
     freed
    -0.83
     wrapped
    -0.83
     doub
    -0.82
    POSITIVE LOGITS
    âĹı
    1.58
    âĸł
    1.40
    ccording
    1.22
    âĺħ
    1.18
    Hardware
    1.15
    âĢ¢
    1.14
     âĹı
    1.10
    Spoiler
    1.08
    Recommend
    1.07
    Developer
    1.06
    Activations Density 1.467%

    No Known Activations