© 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. 10109
    Prev
    Next
    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    parentheses in the text

    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
     sonic
    -0.75
     retard
    -0.74
    irds
    -0.74
     lull
    -0.74
    cules
    -0.73
    utic
    -0.73
     spir
    -0.71
     sav
    -0.68
     psychosis
    -0.68
     interstellar
    -0.68
    POSITIVE LOGITS
    pictured
    1.28
    formerly
    1.23
    sic
    1.15
    among
    1.14
    who
    1.11
    via
    1.09
    Bloomberg
    1.07
    whose
    1.05
    both
    1.03
    see
    1.01
    Activations Density 0.076%

    No Known Activations