© 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. 4469
    Prev
    Next
    INDEX
    Explanations

    Last names of people, primarily with "owitz" and "atton" endings

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly those involved in notable contexts

    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
     runaway
    -0.86
     Kerala
    -0.68
     Chilean
    -0.67
     distracted
    -0.62
     kindred
    -0.62
     Brazilian
    -0.62
     Libertarian
    -0.60
     vain
    -0.59
     Portuguese
    -0.59
    usercontent
    -0.59
    POSITIVE LOGITS
    owitz
    1.21
    enegger
    1.09
    itsch
    1.02
    wald
    0.93
    eln
    0.91
    stein
    0.90
    feld
    0.89
    ansky
    0.88
    itz
    0.83
    roth
    0.83
    Activations Density 0.012%

    No Known Activations