© 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. 805
    Prev
    Next
    INDEX
    Explanations

    questions about hypothetical scenarios

    oai_token-act-pair · gpt-3.5-turbo

    questions that start with "How" or "Would"

    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
    story
    -0.63
    built
    -0.60
    noticed
    -0.60
    claimed
    -0.60
    anie
    -0.58
    Pie
    -0.58
    gat
    -0.57
    meta
    -0.57
    established
    -0.57
    named
    -0.55
    POSITIVE LOGITS
     suffice
    0.79
     be
    0.77
     qualify
    0.72
    yip
    0.69
    terness
    0.69
     happen
    0.69
     anybody
    0.69
     anyone
    0.67
     argue
    0.67
     retaliate
    0.66
    Activations Density 0.050%

    No Known Activations