© 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. 1-RES-JB
    11. 24087
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people, locations, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of specific individuals and their roles or attributes within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Siber
    -0.82
     Kirby
    -0.78
     Haram
    -0.72
     Atkinson
    -0.71
     KC
    -0.69
     Tinker
    -0.69
     Misty
    -0.69
     Chiefs
    -0.68
     SERVICE
    -0.67
     Nid
    -0.66
    POSITIVE LOGITS
    geist
    1.03
    uchin
    1.02
    nuts
    0.96
    ollower
    0.92
    igans
    0.89
    iae
    0.88
    arist
    0.84
    olin
    0.84
    iano
    0.83
    auer
    0.81
    Activations Density 0.018%

    No Known Activations