© 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. 12898
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Micro" followed by a number as a reference to technological products or medical tests

    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
    674
    +0.04
    0.4%
    308
    +0.04
    0.4%
    371
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.04
    0.02
    288
    +0.04
    0.02
    60
    +0.04
    0.01
    Negative Logits
    inia
    -0.30
    inic
    -0.29
     apost
    -0.27
     conflicts
    -0.26
    izations
    -0.26
     vend
    -0.25
     secular
    -0.25
     ðŁij
    -0.25
    weekly
    -0.25
     asc
    -0.25
    POSITIVE LOGITS
    ĸļ
    0.47
    HAEL
    0.38
    cule
    0.36
    ©¶æ¥µ
    0.34
    bial
    0.34
    rity
    0.30
    PORT
    0.30
    phies
    0.30
    rice
    0.30
    erity
    0.29
    Activations Density 0.044%

    No Known Activations