© 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. 4-RES-JB
    11. 1559
    Prev
    Next
    INDEX
    Explanations

    proper nouns of people and places

    oai_token-act-pair · gpt-3.5-turbo

    action verbs that indicate continuity or progression in narrative context

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

    No Comments

    Negative Logits
    Compared
    -0.72
    generated
    -0.66
    respective
    -0.65
    depending
    -0.65
    selves
    -0.64
    establishment
    -0.64
    members
    -0.61
    each
    -0.60
    Higher
    -0.60
    Availability
    -0.58
    POSITIVE LOGITS
     himself
    0.75
     herself
    0.63
    achus
    0.61
     his
    0.60
    ansen
    0.60
     HuffPost
    0.59
     Bust
    0.59
     BART
    0.58
     scathing
    0.57
     puck
    0.57
    Activations Density 0.588%

    No Known Activations