Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 3554
    Prev
    Next
    INDEX
    Explanations

    words related to a specific mythical or fictional entity, potentially associated with art and Kickstarter projects

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter combinations related to a specific name or term

    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
    lished
    -0.65
     elig
    -0.60
     Entry
    -0.59
     fingerprint
    -0.59
     appre
    -0.59
     partName
    -0.58
     nonexistent
    -0.58
     Alleg
    -0.58
    OTAL
    -0.58
     Cortex
    -0.57
    POSITIVE LOGITS
    igans
    0.92
    felt
    0.83
    ghan
    0.82
    chenko
    0.81
    kamp
    0.78
    acho
    0.76
    bugs
    0.75
    zman
    0.74
    lower
    0.73
    azy
    0.73
    Activations Density 0.069%

    No Known Activations