© 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. 15226
    Prev
    Next
    INDEX
    Explanations

    the word "genius" and its variants

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "genius" and its variations

    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
     Continued
    -0.86
    aver
    -0.78
    atern
    -0.75
    vati
    -0.72
    asca
    -0.66
    eden
    -0.63
    avia
    -0.62
    violence
    -0.62
    resp
    -0.62
    avan
    -0.61
    POSITIVE LOGITS
     genius
    1.08
    smanship
    0.89
     Genius
    0.82
     Doodle
    0.82
    iuses
    0.80
    stroke
    0.73
    minded
    0.71
    plex
    0.70
    ocratic
    0.69
     talent
    0.68
    Activations Density 0.010%

    No Known Activations