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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 7-RES-JB
    6. 23250
    Prev
    Next
    INDEX
    Explanations

    mentions of participation in All-Star events and accolades in sports

    oai_token-act-pair · gpt-3.5-turbo

    references to the "All-Star" events in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    perm
    -0.83
    ²¾
    -0.79
    hr
    -0.76
    haar
    -0.74
    alys
    -0.73
    ör
    -0.70
    »Ĵ
    -0.69
    okia
    -0.69
    nai
    -0.69
    flows
    -0.69
    POSITIVE LOGITS
    osterone
    0.88
     Baseball
    0.85
     Weekend
    0.85
     Winners
    0.77
    ournament
    0.75
    NBA
    0.74
     festivities
    0.74
     preseason
    0.73
     Sporting
    0.72
     Hon
    0.72
    Activations Density 0.024%

    No Known Activations