© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 18288
    Prev
    Next
    INDEX
    Explanations

    questions or sentences that are inquiring about specific topics or subjects

    oai_token-act-pair · gpt-3.5-turbo

    questions that begin with "does."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fights
    -0.81
    isers
    -0.80
    agonists
    -0.78
    isphere
    -0.76
    runners
    -0.76
    boats
    -0.75
    eers
    -0.74
    offs
    -0.73
    bags
    -0.71
    asers
    -0.71
    POSITIVE LOGITS
    olation
    0.97
     anyone
    0.84
     anybody
    0.82
    berra
    0.81
    olated
    0.76
    omething
    0.74
    olate
    0.69
    nt
    0.67
    omorphic
    0.66
    terness
    0.65
    Activations Density 0.051%

    No Known Activations