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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-RES-JB
    6. 22216
    Prev
    Next
    INDEX
    Explanations

    references to the MMA fighter Conor McGregor

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Conor McGregor."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.79
     Democr
    -0.74
    heimer
    -0.69
     revolving
    -0.68
    DIR
    -0.66
    031
    -0.66
     Decay
    -0.66
    uds
    -0.64
    PsyNetMessage
    -0.64
    grades
    -0.64
    POSITIVE LOGITS
     McGregor
    1.16
    inational
    0.91
    awan
    0.90
     Conor
    0.86
    weights
    0.83
    riots
    0.82
    weight
    0.82
    ricanes
    0.82
     Ober
    0.82
    agraph
    0.78
    Activations Density 0.007%

    No Known Activations