© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16202
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific terms that are widely recognized or well-known

    oai_token-act-pair · gpt-3.5-turbo

    terms or phrases that refer to entities or concepts that are recognized under the descriptor "known."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    plet
    -0.91
    erva
    -0.84
    otion
    -0.82
    rentice
    -0.78
    oples
    -0.77
    oton
    -0.76
    odder
    -0.76
    otom
    -0.75
    ertation
    -0.75
    otos
    -0.72
    POSITIVE LOGITS
    ledged
    0.79
     Known
    0.75
    л
    0.75
    stood
    0.75
    ãĤ¤
    0.74
    cut
    0.73
     BaseType
    0.72
    cuts
    0.71
    Offline
    0.70
     HIP
    0.69
    Activations Density 0.032%

    No Known Activations