© 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. 9-RES-JB
    11. 4892
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms related to procedures, diseases, and research

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health, well-being, and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bikini
    -0.79
     Slim
    -0.65
     rusty
    -0.64
     Logo
    -0.63
     wig
    -0.63
     camel
    -0.62
    BLIC
    -0.60
    hap
    -0.58
     AMER
    -0.58
     taco
    -0.58
    POSITIVE LOGITS
     initiation
    0.94
     onset
    0.91
     itself
    0.86
    thood
    0.84
     regardless
    0.78
     cessation
    0.77
    making
    0.77
     purposes
    0.76
     proceedings
    0.76
     irrespective
    0.76
    Activations Density 0.432%

    No Known Activations