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

    Neuronpedia

    Jacobian LensNEW
    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. 4901
    Prev
    Next
    INDEX
    Explanations

    mentions of something being naked or uncovered

    oai_token-act-pair · gpt-3.5-turbo

    words related to various forms of the word "bake."

    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
    flu
    -0.80
    fighters
    -0.77
    ãĥ£
    -0.72
     Ago
    -0.71
     Ferdinand
    -0.68
    aign
    -0.67
    few
    -0.65
    prev
    -0.63
    ancial
    -0.62
    cour
    -0.61
    POSITIVE LOGITS
    aimon
    0.90
    irt
    0.75
    ewitness
    0.74
    ossier
    0.72
    uthor
    0.71
    ipation
    0.71
    elta
    0.70
     havoc
    0.70
    imentary
    0.69
    hap
    0.69
    Activations Density 0.006%

    No Known Activations