© 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. 9961
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and border crossings

    oai_token-act-pair · gpt-3.5-turbo

    geographical or border-related terms

    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
    STEM
    -0.82
    orians
    -0.76
    chool
    -0.75
     CEOs
    -0.71
     tenants
    -0.70
     architects
    -0.69
     roomm
    -0.69
    owment
    -0.67
     condos
    -0.66
     Architects
    -0.66
    POSITIVE LOGITS
     porous
    1.17
     border
    1.15
    border
    1.14
     Strait
    1.11
     borders
    1.08
     Euph
    1.07
     rivers
    0.98
     waterways
    0.97
     disputed
    0.97
     airspace
    0.96
    Activations Density 0.243%

    No Known Activations