© 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. 9-RES-JB
    11. 16149
    Prev
    Next
    INDEX
    Explanations

    phrases related to geographical locations, particularly borders

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "along" in relation to borders or boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    meg
    -0.74
    ann
    -0.68
    aign
    -0.67
    tu
    -0.66
    atis
    -0.66
    vana
    -0.63
    doms
    -0.63
    TY
    -0.62
    bern
    -0.61
    anish
    -0.61
    POSITIVE LOGITS
    side
    1.00
     routes
    0.90
     highways
    0.89
     Route
    0.85
     corridors
    0.82
     Interstate
    0.82
     shore
    0.81
     route
    0.80
     Aven
    0.80
     roads
    0.80
    Activations Density 0.027%

    No Known Activations