© 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. 6428
    Prev
    Next
    INDEX
    Explanations

    specific entities or concepts related to legal or regulatory frameworks

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal and regulatory issues

    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
    onday
    -0.66
    margin
    -0.65
    inventoryQuantity
    -0.62
    rontal
    -0.60
    edition
    -0.59
    veh
    -0.58
     ted
    -0.58
    etheless
    -0.58
     whirlwind
    -0.56
    enhagen
    -0.56
    POSITIVE LOGITS
     to
    0.69
     into
    0.61
     access
    0.61
    DERR
    0.59
     adopt
    0.58
     sake
    0.57
    '"
    0.57
    iffs
    0.56
    SEE
    0.56
    SPONSORED
    0.56
    Activations Density 0.486%

    No Known Activations