© 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. 17213
    Prev
    Next
    INDEX
    Explanations

    proper nouns that may represent companies, locations, or people

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the syllable "us" and similar phonetic patterns or variants

    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
     caucuses
    -0.66
     cruc
    -0.61
     pus
    -0.60
     WB
    -0.59
     paraly
    -0.57
     deduct
    -0.57
     lull
    -0.57
    px
    -0.56
     captcha
    -0.56
     closet
    -0.55
    POSITIVE LOGITS
    ruary
    1.22
    renheit
    1.13
    owship
    1.06
    gerald
    1.03
    ancial
    1.01
    ilial
    0.94
    uci
    0.90
    acebook
    0.86
    ushima
    0.85
    heit
    0.84
    Activations Density 0.133%

    No Known Activations