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. 8-RES-JB
    6. 20762
    Prev
    Next
    INDEX
    Explanations

    names related to football (soccer) managers

    oai_token-act-pair · gpt-3.5-turbo

    names of football (soccer) managers and their associated context in relation to performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Native
    -0.79
     Polaris
    -0.79
     Sabha
    -0.72
     Sakuya
    -0.72
     Naomi
    -0.72
     Libertarian
    -0.72
     Nek
    -0.71
    ratom
    -0.71
     Scotia
    -0.70
     Vermont
    -0.69
    POSITIVE LOGITS
     coached
    1.15
     oversaw
    1.07
    ovich
    1.00
     coaching
    1.00
    ichick
    0.99
    uden
    0.96
     sacked
    0.95
     preached
    0.92
     overseen
    0.88
     inherited
    0.83
    Activations Density 0.157%

    No Known Activations