© 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. 14683
    Prev
    Next
    INDEX
    Explanations

    content related to various ongoing events and stories, possibly with a focus on legal, political, and community issues

    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
    314
    +0.16
    0.6%
    152
    +0.16
    0.5%
    640
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.16
    0.09
    124
    +0.16
    0.09
    639
    +0.16
    0.08
    Negative Logits
     Cassidy
    -1.03
    achus
    -0.92
     Rocky
    -0.91
     Tactics
    -0.91
     Galileo
    -0.89
     Narc
    -0.89
     Twain
    -0.88
     Trojan
    -0.87
     Sno
    -0.85
     AVG
    -0.85
    POSITIVE LOGITS
    degree
    1.68
    issue
    1.64
    year
    1.63
    percent
    1.50
    years
    1.46
    series
    1.44
    inch
    1.43
    million
    1.43
    bodied
    1.41
    sized
    1.40
    Activations Density 0.752%

    No Known Activations