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. 2-RES-JB
    6. 16554
    Prev
    Next
    INDEX
    Explanations

    terms related to sports seasons

    oai_token-act-pair · gpt-3.5-turbo

    references to sports seasons, particularly in a context related to pre-season and mid-season activities

    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
    ochet
    -0.74
    creen
    -0.70
     Haram
    -0.64
     blazing
    -0.63
     darn
    -0.63
    aghan
    -0.63
    imb
    -0.62
     touchscreen
    -0.61
    arantine
    -0.60
    yz
    -0.60
    POSITIVE LOGITS
    orsi
    0.89
     Nadu
    0.84
    ãĥ¯ãĥ³
    0.82
    ruary
    0.79
    season
    0.76
    adjusted
    0.75
    osterone
    0.74
    DragonMagazine
    0.73
    ı
    0.68
    rawdownloadcloneembedreportprint
    0.68
    Activations Density 0.006%

    No Known Activations