© 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. 18475
    Prev
    Next
    INDEX
    Explanations

    sequential actions in a narrative

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to criminal activities or incidents

    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
    ourcing
    -0.77
    etheless
    -0.71
    instead
    -0.67
    uably
    -0.66
     precedent
    -0.63
    arij
    -0.62
    quickShipAvailable
    -0.62
    tested
    -0.61
    haven
    -0.60
     opio
    -0.60
    POSITIVE LOGITS
     breakfast
    0.73
     farewell
    0.73
    ]]
    0.71
     pane
    0.70
     sentence
    0.70
     procession
    0.69
     lunch
    0.69
     supper
    0.68
     groceries
    0.68
     recess
    0.67
    Activations Density 0.653%

    No Known Activations