© 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. 0-RES-JB
    11. 16803
    Prev
    Next
    INDEX
    Explanations

    mentions of specific entities or locations followed by the word "Zone."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Zone" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    achus
    -0.78
    clud
    -0.73
    asio
    -0.72
    LECT
    -0.70
    cffff
    -0.68
    oneliness
    -0.67
    unin
    -0.66
    dom
    -0.66
    rawdownloadcloneembedreportprint
    -0.65
     mathemat
    -0.64
    POSITIVE LOGITS
    Zone
    0.82
    anza
    0.62
     reversed
    0.62
     Pact
    0.61
     carrots
    0.60
     aviation
    0.60
     td
    0.59
     Aviation
    0.59
     gone
    0.58
     pilots
    0.58
    Activations Density 0.001%

    No Known Activations