© 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. 17724
    Prev
    Next
    INDEX
    Explanations

    mentions of the specific person "Floyd Mayweather"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the boxer Floyd Mayweather

    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
    umbn
    -0.79
    PsyNetMessage
    -0.78
    CAP
    -0.75
    egal
    -0.75
    gger
    -0.71
    ahime
    -0.70
    ffic
    -0.70
    skirts
    -0.67
    erous
    -0.67
    peer
    -0.67
    POSITIVE LOGITS
     Mayweather
    1.37
     Floyd
    1.16
    mania
    0.81
    Mania
    0.80
    nuts
    0.79
    \\\\\\\\\\\\\\\\
    0.74
    \\\\\\\\
    0.72
    ouncing
    0.67
    ruary
    0.66
    bags
    0.66
    Activations Density 0.010%

    No Known Activations