© 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. 20326
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Cap"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Cap" and its variations or context

    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
    ĪĴ
    -0.86
    hower
    -0.84
    Reloaded
    -0.82
    ãģį
    -0.75
    WAYS
    -0.74
     silence
    -0.74
    perse
    -0.72
    ĸļ
    -0.70
     td
    -0.67
     else
    -0.63
    POSITIVE LOGITS
    itals
    1.13
     Cap
    1.13
    itol
    1.12
    Cap
    1.00
    illus
    0.95
    illary
    0.94
    abulary
    0.93
    aldi
    0.93
    acity
    0.93
    cap
    0.92
    Activations Density 0.004%

    No Known Activations