© 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. 17571
    Prev
    Next
    INDEX
    Explanations

    timestamps

    oai_token-act-pair · gpt-3.5-turbo

    periods in text

    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
    enegger
    -0.68
    enhagen
    -0.57
    æ³
    -0.57
     acknowled
    -0.57
    hett
    -0.56
     unintended
    -0.55
     è£ıè
    -0.54
     KH
    -0.53
     Cosponsors
    -0.53
     longevity
    -0.53
    POSITIVE LOGITS
    days
    0.82
    noon
    0.78
    minute
    0.78
    teenth
    0.77
    month
    0.76
    Downloadha
    0.75
    pillar
    0.72
    dozen
    0.71
    clock
    0.70
    bath
    0.69
    Activations Density 0.022%

    No Known Activations