© 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. 588
    Prev
    Next
    INDEX
    Explanations

    words starting with "Bod" regardless of what follows

    oai_token-act-pair · gpt-4-turbo

    occurrences of the word "Bod"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Bod" and related variations

    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
    ICO
    -0.82
    IELD
    -0.71
    ablishment
    -0.71
     Zucker
    -0.68
    ADE
    -0.67
    Nazi
    -0.66
     PowerPoint
    -0.66
    ################
    -0.65
    IVE
    -0.63
    577
    -0.63
    POSITIVE LOGITS
     Bod
    1.03
     nodd
    1.03
    iless
    0.99
    axter
    0.96
    hid
    0.96
    etooth
    0.95
    guards
    0.94
    ysc
    0.94
     unden
    0.93
     challeng
    0.91
    Activations Density 0.007%

    No Known Activations