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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-RES-JB
    6. 2438
    Prev
    Next
    INDEX
    Explanations

    references to sporting activities, teams, and events

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sports teams, particularly "Sporting" and "Milan"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erto
    -0.75
    rend
    -0.74
    inately
    -0.65
    arded
    -0.64
    erent
    -0.64
    rants
    -0.63
    dies
    -0.63
     poker
    -0.63
    UGE
    -0.61
     whim
    -0.61
    POSITIVE LOGITS
    atorium
    0.88
    itas
    0.84
    owicz
    0.84
    owski
    0.82
    ovie
    0.79
     Ventura
    0.78
    ovich
    0.77
    ovan
    0.76
     Rica
    0.75
    omnia
    0.74
    Activations Density 0.046%

    No Known Activations