© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4504
    Prev
    Next
    INDEX
    Explanations

    locations based on distance, particularly focusing on proximity to a specific point

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating distance or proximity

    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
     Metatron
    -0.82
    SourceFile
    -0.69
    ãĥĥãĥī
    -0.65
    uld
    -0.63
     Dwell
    -0.62
    rodu
    -0.61
    Marginal
    -0.60
    tek
    -0.60
    YN
    -0.59
    Ns
    -0.59
    POSITIVE LOGITS
     apiece
    0.99
     mosqu
    0.71
     suspended
    0.67
    astern
    0.65
    NetMessage
    0.65
     each
    0.62
     landfall
    0.61
     gestation
    0.61
     separating
    0.61
    icz
    0.61
    Activations Density 0.112%

    No Known Activations