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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 0-RES-JB
    6. 23465
    Prev
    Next
    INDEX
    Explanations

    the name "Shapiro" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly Ben Shapiro and Shannon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Äĩ
    -0.76
     cad
    -0.73
    olves
    -0.73
     Borg
    -0.70
    bos
    -0.70
     fer
    -0.67
    mo
    -0.67
     Ep
    -0.66
     illeg
    -0.66
     inf
    -0.65
    POSITIVE LOGITS
     Shannon
    1.99
     Shapiro
    1.96
     Sho
    1.92
    Sh
    1.89
     Sha
    1.73
     Shim
    1.72
     Sharma
    1.70
     Shane
    1.69
    SHA
    1.68
     Sh
    1.67
    Activations Density 0.048%

    No Known Activations