© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 19477
    Prev
    Next
    INDEX
    Explanations

    words related to a specific sports league, possibly related to soccer, specifically focusing on achievements, ranking, and player or team performance

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "premier" or "premature" in various contexts

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

    No Comments

    Negative Logits
     MacArthur
    -0.84
    glers
    -0.83
    meyer
    -0.78
    gerald
    -0.75
    ãĥīãĥ©ãĤ´ãĥ³
    -0.75
     Hedge
    -0.74
    ger
    -0.71
    ãĥŃ
    -0.70
    geist
    -0.69
     Grail
    -0.69
    POSITIVE LOGITS
    ises
    1.07
    antle
    1.06
    iership
    1.06
    ortal
    1.05
     prem
    1.03
    etheus
    0.97
    odic
    0.93
    asks
    0.88
    igrate
    0.87
    ise
    0.87
    Activations Density 0.010%

    No Known Activations