© 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. 16769
    Prev
    Next
    INDEX
    Explanations

    names related to a specific individual, likely Governor Mark Dayton

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific people and locations, particularly related to governance and events

    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
    ariat
    -0.83
    bery
    -0.78
    ystem
    -0.75
    ATHER
    -0.73
    berman
    -0.72
    rooms
    -0.71
    Correction
    -0.70
    ADA
    -0.68
    ãģ®å
    -0.68
    CVE
    -0.67
    POSITIVE LOGITS
     Dayton
    1.01
     Sparkle
    0.88
    £ı
    0.87
    bley
    0.78
    hyde
    0.76
    ©¶æ¥µ
    0.75
    eneg
    0.74
    ellen
    0.73
    etheless
    0.72
    ength
    0.71
    Activations Density 0.008%

    No Known Activations