© 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. 10-RES-JB
    11. 22217
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations, specifically those starting with "Santa"

    oai_token-act-pair · gpt-3.5-turbo

    references to the geographical location of Santa and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orph
    -0.76
    epad
    -0.72
    bill
    -0.69
    edly
    -0.69
    ochond
    -0.68
    ERG
    -0.67
    ski
    -0.65
    buffer
    -0.64
     Lithuan
    -0.63
    ered
    -0.63
    POSITIVE LOGITS
     Claus
    1.38
     Clara
    1.29
     Monica
    1.24
     Cruz
    1.17
     Barbara
    1.16
     Ana
    1.14
     Rosa
    1.11
     Clause
    1.04
     Clar
    1.03
    Cruz
    0.96
    Activations Density 0.020%

    No Known Activations