© 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. 10-RES-JB
    11. 2779
    Prev
    Next
    INDEX
    Explanations

    mentions of student-athletes and athletic activities within an educational context

    oai_token-act-pair · gpt-3.5-turbo

    references to student-athletes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shorth
    -0.71
     sterling
    -0.67
     Reloaded
    -0.63
     Sahara
    -0.62
    ITED
    -0.61
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.59
    INC
    -0.58
     Wizard
    -0.58
     mosaic
    -0.58
     liking
    -0.57
    POSITIVE LOGITS
    aniel
    1.27
    lete
    1.22
    ouse
    1.19
    reshold
    1.18
    alon
    1.16
    urst
    1.07
    letes
    1.06
    orned
    1.06
    orne
    1.03
    ouses
    1.03
    Activations Density 0.035%

    No Known Activations