© 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. 15187
    Prev
    Next
    INDEX
    Explanations

    questions or statements inquiring about the outcome or progress of a situation

    oai_token-act-pair · gpt-3.5-turbo

    inquiries related to outcomes or consequences

    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
    riter
    -0.71
    "}],"
    -0.68
    archives
    -0.65
     WATCHED
    -0.63
    ul
    -0.63
    UTH
    -0.62
    visory
    -0.62
    athom
    -0.61
    apt
    -0.59
    ulo
    -0.59
    POSITIVE LOGITS
     reaction
    0.81
     reactions
    0.71
     fuss
    0.70
     fared
    0.69
    okin
    0.61
     attrition
    0.61
     truce
    0.60
     shenanigans
    0.59
     soph
    0.59
     develops
    0.59
    Activations Density 0.086%

    No Known Activations