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. 6-RES-JB
    6. 6961
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports performances, such as winning games or matches

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics related to sports performance

    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
    dor
    -0.81
    anth
    -0.79
    helle
    -0.70
    oola
    -0.69
    abal
    -0.67
    oult
    -0.66
     insign
    -0.66
    atom
    -0.65
    orah
    -0.64
    apa
    -0.63
    POSITIVE LOGITS
     outings
    1.05
     postseason
    0.85
     seasons
    0.83
     unbeaten
    0.81
     appearances
    0.80
     matchups
    0.79
     consecutive
    0.79
     occasions
    0.76
     innings
    0.75
     defensively
    0.75
    Activations Density 0.274%

    No Known Activations