© 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. 2-RES-JB
    11. 9357
    Prev
    Next
    INDEX
    Explanations

    names or references related to people or entities ending in "ucci"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly Anthony Scaramucci and Ben Shapiro

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĦ
    -0.73
     Desire
    -0.64
    IFA
    -0.64
    Rust
    -0.64
     robber
    -0.63
     abiding
    -0.62
     Libertarian
    -0.62
    seeing
    -0.61
    coat
    -0.60
    less
    -0.60
    POSITIVE LOGITS
    ucci
    1.33
    issance
    0.93
    cci
    0.91
    atto
    0.90
    ollah
    0.87
    acci
    0.84
    ieri
    0.83
    ombo
    0.82
    angelo
    0.80
    kson
    0.79
    Activations Density 0.005%

    No Known Activations