© 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. 10-RES-JB
    11. 10753
    Prev
    Next
    INDEX
    Explanations

    sentences related to legal matters and consequences

    oai_token-act-pair · gpt-3.5-turbo

    references to potential harmful actions or conditions, particularly related to health and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carnage
    -0.73
     Skydragon
    -0.72
     Allies
    -0.72
    eers
    -0.70
     Survivors
    -0.65
    oday
    -0.65
    ESCO
    -0.64
    ccording
    -0.63
    ĸļ
    -0.62
    ebus
    -0.62
    POSITIVE LOGITS
    wu
    0.72
    |
    0.69
    nob
    0.65
     gmaxwell
    0.63
    bas
    0.62
    uno
    0.61
    hao
    0.59
     prin
    0.59
     <<
    0.57
     *
    0.56
    Activations Density 0.130%

    No Known Activations