© 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. 11-RES-JB
    11. 22550
    Prev
    Next
    INDEX
    Explanations

    questions indicating skepticism, disbelief, or curiosity

    oai_token-act-pair · gpt-3.5-turbo

    rhetorical questions questioning the rationale behind certain actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    catentry
    -0.75
    swick
    -0.70
    iasco
    -0.68
    moil
    -0.66
    iHUD
    -0.64
    ixel
    -0.64
    usk
    -0.63
    insula
    -0.62
    ãĤ©
    -0.62
     highlighted
    -0.62
    POSITIVE LOGITS
     anyone
    1.43
     anybody
    1.40
     someone
    0.99
     sane
    0.99
     ANY
    0.98
     any
    0.94
     somebody
    0.93
     civilized
    0.88
     mortals
    0.86
     you
    0.83
    Activations Density 0.266%

    No Known Activations