© 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. 8-RES-JB
    11. 4611
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical information related to sports performances

    oai_token-act-pair · gpt-3.5-turbo

    statistical data related to sports performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mobil
    -0.76
     Malaysia
    -0.72
    icultural
    -0.71
     organisers
    -0.71
    mop
    -0.69
     postp
    -0.68
     administration
    -0.68
    mission
    -0.67
     presenter
    -0.66
     mediation
    -0.65
    POSITIVE LOGITS
     averaged
    1.11
     averaging
    1.10
    Percent
    1.04
     averages
    1.04
     Adjusted
    1.02
     (.
    0.98
    adjusted
    0.95
     regress
    0.94
    Ranked
    0.90
     statistically
    0.89
    Activations Density 0.484%

    No Known Activations