© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 21754
    Prev
    Next
    INDEX
    Explanations

    adjectives representing intensity or scale

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to potential outcomes or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nar
    -0.74
    antic
    -0.70
    stice
    -0.70
     Centauri
    -0.69
    scope
    -0.67
    Canadian
    -0.66
    Å
    -0.63
    ses
    -0.63
    ashi
    -0.63
    anc
    -0.63
    POSITIVE LOGITS
     WHEN
    1.36
     whenever
    1.08
     if
    1.08
     when
    1.04
     unless
    0.96
     BEFORE
    0.92
    when
    0.90
     WHERE
    0.85
     When
    0.84
     AFTER
    0.84
    Activations Density 0.177%

    No Known Activations