© 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. 4-RES-JB
    11. 14571
    Prev
    Next
    INDEX
    Explanations

    words containing the specific sequence "ough"

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the substring "ough" in various contexts

    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
     Luthor
    -0.72
    HOU
    -0.66
     Leviathan
    -0.63
     Miranda
    -0.60
     Takeru
    -0.60
    vier
    -0.59
    egal
    -0.59
     Metatron
    -0.58
     Titan
    -0.58
     Pegasus
    -0.58
    POSITIVE LOGITS
    sburgh
    0.87
    é¾įåĸļ士
    0.83
    ness
    0.82
    hesda
    0.80
    tyard
    0.78
    nut
    0.77
    ricanes
    0.74
    lins
    0.73
    nesses
    0.73
    ãĤ¡
    0.73
    Activations Density 0.009%

    No Known Activations