© 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. 2-RES-JB
    11. 11106
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of people or organizations

    oai_token-act-pair · gpt-3.5-turbo

    names or references related to individuals involved in a specific narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ank
    -0.72
     Chains
    -0.70
    Charge
    -0.70
     Ces
    -0.69
     largeDownload
    -0.69
    oÄŁ
    -0.69
    =-=-=-=-
    -0.67
     ALSO
    -0.67
     Estate
    -0.66
     proble
    -0.65
    POSITIVE LOGITS
    spread
    0.76
    bath
    0.75
    efficiency
    0.75
    uckland
    0.74
    mopolitan
    0.74
    balanced
    0.74
    mond
    0.73
    board
    0.71
    iversity
    0.71
    bowl
    0.69
    Activations Density 0.000%

    No Known Activations