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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3267
    Prev
    Next
    INDEX
    Explanations

    references to sports leagues, primarily focusing on the American League (AL) in baseball

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sports leagues

    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
    ãĥ¼ãĥĨãĤ£
    -1.06
    achu
    -0.93
     Chaser
    -0.91
    enegger
    -0.89
     {*
    -0.87
     CLSID
    -0.81
    ãĤ¡
    -0.81
    cdn
    -0.81
    ãĥ¯
    -0.79
    intendent
    -0.78
    POSITIVE LOGITS
    manac
    1.01
    ighting
    0.87
    abama
    0.87
    ibaba
    0.84
    gebra
    0.83
    ocal
    0.83
    ERT
    0.82
    ogical
    0.77
    TIT
    0.76
    usions
    0.75
    Activations Density 0.010%

    No Known Activations