© 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. 11-RES-JB
    11. 16507
    Prev
    Next
    INDEX
    Explanations

    references to statistics and achievements in sports

    oai_token-act-pair · gpt-3.5-turbo

    metrics related to career performance in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.64
    agents
    -0.62
    ochemistry
    -0.60
    ayers
    -0.58
    rices
    -0.58
     preparations
    -0.57
    gered
    -0.57
    ospace
    -0.56
     Mehran
    -0.56
    andom
    -0.56
    POSITIVE LOGITS
    high
    1.36
     highs
    1.32
     lows
    1.21
    low
    1.15
     low
    1.10
    best
    1.07
    worst
    1.07
     high
    1.05
     HIGH
    1.05
     lowest
    0.98
    Activations Density 0.093%

    No Known Activations