© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11430
    Prev
    Next
    INDEX
    Explanations

    the word "zone."

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical or designated zones, particularly in a conflict or military context

    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
    mort
    -0.74
    asa
    -0.73
    hester
    -0.70
    icians
    -0.65
    tis
    -0.64
    mot
    -0.63
    pring
    -0.63
     Cogn
    -0.63
     induct
    -0.63
     Hep
    -0.62
    POSITIVE LOGITS
     zone
    4.04
     zones
    3.28
     Zone
    3.01
    zone
    2.80
    Zone
    2.37
     area
    1.30
     zoning
    1.24
     radius
    1.11
     territory
    1.10
     Area
    1.10
    Activations Density 0.026%

    No Known Activations