© 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. 8-RES-JB
    11. 6892
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to various entities such as individuals, organizations, and locations

    oai_token-act-pair · gpt-3.5-turbo

    names of people, organizations, and locations associated with significant events or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    untarily
    -0.67
    ezvous
    -0.66
    xtap
    -0.65
    nown
    -0.63
    iannopoulos
    -0.62
     Cosponsors
    -0.61
    tery
    -0.60
    heid
    -0.60
    usalem
    -0.59
    olicited
    -0.58
    POSITIVE LOGITS
     sake
    0.94
     purposes
    0.91
     coffers
    0.87
     brass
    0.71
     reasons
    0.68
     because
    0.67
     enthusi
    0.67
     shareholders
    0.67
    payers
    0.66
     faithful
    0.66
    Activations Density 0.559%

    No Known Activations