© 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. 22417
    Prev
    Next
    INDEX
    Explanations

    questions and hypothetical scenarios

    oai_token-act-pair · gpt-3.5-turbo

    interrogative words and phrases that initiate questions or inquiries

    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
     semin
    -0.61
    yrim
    -0.61
     silenced
    -0.61
     Interior
    -0.61
     Janeiro
    -0.60
     Pione
    -0.60
     Greenwood
    -0.60
    ridges
    -0.59
     foremost
    -0.58
     installations
    -0.57
    POSITIVE LOGITS
    lihood
    0.92
    -
    0.84
    %-
    0.79
    -$
    0.79
    '-
    0.74
    advertising
    0.74
    -'
    0.73
    ciation
    0.72
     clause
    0.70
    "-
    0.69
    Activations Density 0.258%

    No Known Activations