© 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. 2500
    Prev
    Next
    INDEX
    Explanations

    numbers represented as a percentage

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical percentages

    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
    IRT
    -0.77
     Horizons
    -0.73
    ITED
    -0.71
    çīĪ
    -0.70
    æ©
    -0.70
    ieties
    -0.68
    士
    -0.68
    ebus
    -0.68
    engeance
    -0.67
    GBT
    -0.67
    POSITIVE LOGITS
     (%)
    0.88
     percentage
    0.82
     percentages
    0.81
    pointer
    0.76
     accuracy
    0.74
    hetical
    0.73
     ceilings
    0.72
     coefficient
    0.72
    payer
    0.70
    ennial
    0.69
    Activations Density 0.036%

    No Known Activations