© 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. 17309
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, specifically the White House and its vicinity

    oai_token-act-pair · gpt-3.5-turbo

    specific locations and associated events

    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
     Albion
    -0.78
    Ont
    -0.76
     Scythe
    -0.73
     Hav
    -0.72
     Gladiator
    -0.72
     Leth
    -0.70
     Bram
    -0.69
    alys
    -0.69
     Reson
    -0.69
    liga
    -0.68
    POSITIVE LOGITS
    OTUS
    1.72
     presidents
    1.67
     Oval
    1.66
     Presidents
    1.56
     Spicer
    1.47
     presidency
    1.47
     Nixon
    1.46
     President
    1.44
     inauguration
    1.44
     administrations
    1.43
    Activations Density 0.783%

    No Known Activations