© 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. 8034
    Prev
    Next
    INDEX
    Explanations

    specific numerical values or codes

    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
    208
    +0.13
    0.6%
    166
    +0.13
    0.6%
    578
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    208
    +0.13
    0.03
    701
    +0.13
    0.03
    232
    +0.12
    0.03
    Negative Logits
     streng
    -0.80
    £ı
    -0.78
    assetsadobe
    -0.77
     lawy
    -0.74
     Pione
    -0.72
     confir
    -0.71
    ķ
    -0.71
     comprom
    -0.70
     cannabin
    -0.70
    ¥µ
    -0.69
    POSITIVE LOGITS
    odus
    1.09
    imity
    1.09
    press
    0.98
    ample
    0.94
    actly
    0.94
    ercise
    0.94
    isting
    0.94
    aminer
    0.91
    posed
    0.90
    cellence
    0.89
    Activations Density 0.212%

    No Known Activations