© 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. 4-RES-JB
    11. 10137
    Prev
    Next
    INDEX
    Explanations

    references to the term "Pitt" followed by a number that is reflected in the high activation values, indicating a specific focus on this keyword

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Pitt" or related references, indicating focus on a specific entity or location

    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
    ãĤ°
    -0.68
    claimer
    -0.67
    Copy
    -0.64
    ////////////////
    -0.64
    eering
    -0.62
    âĸ¬âĸ¬
    -0.62
    BOOK
    -0.62
    ãĥĪ
    -0.62
    ATIVE
    -0.61
    @@@@
    -0.61
    POSITIVE LOGITS
    sburgh
    1.61
    sburg
    1.44
    sylvania
    1.19
     Pitt
    1.04
    Pitt
    0.90
    s
    0.88
    sylv
    0.85
    shire
    0.85
    burgh
    0.85
    man
    0.82
    Activations Density 0.005%

    No Known Activations