© 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. 4-RES-JB
    11. 14778
    Prev
    Next
    INDEX
    Explanations

    mentions of locations near coastlines, specifically with high relevance to the term "coast"

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic locations, particularly coastal areas

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

    No Comments

    Negative Logits
    chel
    -0.79
    thood
    -0.77
    VK
    -0.76
    Lens
    -0.72
    æł
    -0.71
    728
    -0.71
    akia
    -0.71
    chy
    -0.70
    itsch
    -0.70
     Machina
    -0.69
    POSITIVE LOGITS
    lines
    1.05
     coast
    1.05
     shore
    0.85
     wip
    0.82
    line
    0.81
     cliffs
    0.81
     Coast
    0.81
     coastline
    0.78
    side
    0.78
     beaches
    0.74
    Activations Density 0.010%

    No Known Activations