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

    Neuronpedia

    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. 6-RES-JB
    11. 18391
    Prev
    Next
    INDEX
    Explanations

    statements related to legal or moral implications and consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating reasonable beliefs related to danger and injury

    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
    DK
    -0.58
     Patreon
    -0.56
    ahime
    -0.56
    MK
    -0.55
    iets
    -0.55
    MSN
    -0.55
    Knight
    -0.54
     Jed
    -0.54
    Dialogue
    -0.54
    emonium
    -0.54
    POSITIVE LOGITS
    ).[
    0.76
    Downloadha
    0.73
    )).
    0.72
     harm
    0.69
    ").
    0.68
    )."
    0.67
     biological
    0.62
     or
    0.62
    azo
    0.61
     detriment
    0.61
    Activations Density 2.096%

    No Known Activations