© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 3758
    Prev
    Next
    INDEX
    Explanations

    proper names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Booth."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     skelet
    -0.83
     retaliate
    -0.78
    atives
    -0.77
    ccording
    -0.77
    azeera
    -0.73
     cradle
    -0.72
    ators
    -0.71
     Riy
    -0.71
     Frankenstein
    -0.66
    ateur
    -0.66
    POSITIVE LOGITS
     Booth
    1.31
    sworth
    0.96
    ooth
    0.93
     Lect
    0.85
    ridge
    0.83
    shot
    0.80
    shire
    0.77
    cock
    0.76
    bum
    0.76
    shaw
    0.75
    Activations Density 0.014%

    No Known Activations