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. 2-RES-JB
    6. 19233
    Prev
    Next
    INDEX
    Explanations

    phrases related to baseball hitting actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to hitting in various contexts, particularly in sports

    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
    pires
    -0.87
    cia
    -0.83
    ¥µ
    -0.68
    orld
    -0.65
    inent
    -0.64
    yles
    -0.64
    otive
    -0.62
    transfer
    -0.60
     Legends
    -0.60
     Costume
    -0.58
    POSITIVE LOGITS
    hitting
    0.94
    hit
    0.93
     hit
    0.85
    ched
    0.81
    ãĥĺ
    0.79
     hitting
    0.79
    gerald
    0.79
     hits
    0.77
    achi
    0.74
    chens
    0.73
    Activations Density 0.019%

    No Known Activations