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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 3
    Prev
    Next
    INDEX
    Explanations

    athletic statistics and player biographical information

    oai_token-act-pair · gpt-3.5-turbo

    statistical data and metrics related to sports performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bak
    -0.73
     caf
    -0.71
     investig
    -0.66
     Moj
    -0.65
     Cater
    -0.64
    netflix
    -0.64
     themed
    -0.63
     catering
    -0.63
     nort
    -0.62
    enegger
    -0.61
    POSITIVE LOGITS
    BIP
    1.10
    Avg
    1.05
     Ratio
    1.03
    Percent
    0.96
     ratio
    0.94
    %:
    0.91
    uracy
    0.88
    ENGTH
    0.86
    %.
    0.86
    total
    0.86
    Activations Density 0.145%

    No Known Activations