© 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. 11-RES-JB
    11. 22580
    Prev
    Next
    INDEX
    Explanations

    locations near borders

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations and borders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DAY
    -0.80
    rix
    -0.75
     alone
    -0.74
    Premium
    -0.74
    ocument
    -0.73
     apart
    -0.73
     thereafter
    -0.72
    eenth
    -0.71
    Anonymous
    -0.71
    uits
    -0.68
    POSITIVE LOGITS
     intersection
    1.11
     entrance
    1.08
     junction
    1.05
     nearest
    1.00
     edge
    0.99
     border
    0.95
     coast
    0.95
     airport
    0.94
     epic
    0.93
     shores
    0.92
    Activations Density 0.119%

    No Known Activations