© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 9379
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "Ċ" and followed by a numeric value indicating emphasis or importance

    oai_token-act-pair · gpt-3.5-turbo

    instances of high numerical values indicating emphasis or urgency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tram
    -0.82
     neighb
    -0.80
     emancipation
    -0.80
     scripting
    -0.78
     covenant
    -0.77
     bundled
    -0.77
     ende
    -0.76
     quir
    -0.74
     migration
    -0.73
     derby
    -0.72
    POSITIVE LOGITS
    Advertisements
    1.29
    https
    1.29
    If
    1.22
    MAL
    1.18
    Looks
    1.17
    What
    1.17
    We
    1.17
    âĢ¢
    1.16
    When
    1.16
    Why
    1.15
    Activations Density 0.171%

    No Known Activations