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. 3469
    Prev
    Next
    INDEX
    Explanations

    terms related to fantasy sports

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fantasy football

    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
    ĸļ
    -0.91
    chan
    -0.77
    allic
    -0.76
     ALP
    -0.74
    PLA
    -0.72
     ministries
    -0.71
     Lego
    -0.70
    OPA
    -0.69
     Transport
    -0.68
    pi
    -0.68
    POSITIVE LOGITS
     rankings
    1.17
     Rankings
    1.13
    verages
    1.12
     tracker
    0.98
     Ratings
    0.96
     averages
    0.95
     averaging
    0.94
     analyst
    0.93
     ratings
    0.92
     leagues
    0.91
    Activations Density 0.298%

    No Known Activations