© 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. 1-RES-JB
    11. 24005
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Gabriel" with various intensities based on the relevance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Gabriel."

    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
    under
    -0.81
    ORE
    -0.70
    available
    -0.70
    perature
    -0.68
    unders
    -0.66
    iversity
    -0.65
    req
    -0.64
     Âł Âł Âł Âł
    -0.62
    issue
    -0.62
    onut
    -0.62
    POSITIVE LOGITS
     Gabriel
    1.11
     Garc
    0.92
    Gab
    0.90
    raham
    0.86
     Byrne
    0.80
    theless
    0.79
    riel
    0.78
    pour
    0.77
    renheit
    0.76
    sson
    0.76
    Activations Density 0.007%

    No Known Activations