© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15188
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and societal issues, especially those involving regulations and judgments

    oai_token-act-pair · gpt-3.5-turbo

    references to medical procedures and their implications

    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
    eatures
    -0.62
     Osw
    -0.61
     consists
    -0.60
     Ambrose
    -0.60
    achu
    -0.59
    levision
    -0.58
     acron
    -0.56
     encompasses
    -0.55
     understatement
    -0.55
     Alphabet
    -0.54
    POSITIVE LOGITS
     etc
    0.92
    )).
    0.92
     or
    0.90
    ?".
    0.85
    .?
    0.82
     undet
    0.81
    ?).
    0.79
    '.
    0.76
    !".
    0.74
    )?
    0.74
    Activations Density 1.261%

    No Known Activations