© 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. 3-RES-JB
    11. 10623
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to science fiction and gaming

    oai_token-act-pair · gpt-3.5-turbo

    names and terms related to popular culture, specifically from the Star Wars universe and video games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uracy
    -0.75
    uity
    -0.70
    代
    -0.67
    lisher
    -0.66
    ãĥĥãĤ¯
    -0.65
    uation
    -0.64
     synd
    -0.63
    iard
    -0.63
    uring
    -0.62
    rogens
    -0.62
    POSITIVE LOGITS
     Solo
    1.04
     Skywalker
    0.89
    Tang
    0.79
    ngth
    0.77
    lake
    0.75
    Ton
    0.74
    qqa
    0.73
     Tray
    0.72
     Rivals
    0.71
    Mid
    0.68
    Activations Density 0.007%

    No Known Activations