© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17613
    Prev
    Next
    INDEX
    Explanations

    keywords related to online activity metrics and award systems

    oai_token-act-pair · gpt-3.5-turbo

    terms related to online activity and engagement 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
    mus
    -0.80
    ibur
    -0.71
     Elias
    -0.68
    andre
    -0.67
    ibi
    -0.67
    agos
    -0.67
     Rafael
    -0.65
    bash
    -0.64
    rend
    -0.63
    cer
    -0.63
    POSITIVE LOGITS
    Merit
    0.94
    ertodd
    0.90
     ACTIONS
    0.78
    risome
    0.74
    aceous
    0.73
     seriousness
    0.71
     Messages
    0.70
    acters
    0.65
    Activity
    0.64
    =>
    0.64
    Activations Density 0.027%

    No Known Activations