© 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. 6345
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific experiments or operational activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to experimental and operational processes

    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
    borough
    -0.80
    conom
    -0.75
    ets
    -0.74
    pered
    -0.73
    lyn
    -0.73
    galitarian
    -0.72
    kins
    -0.71
    xual
    -0.71
    Downloadha
    -0.71
    awaru
    -0.69
    POSITIVE LOGITS
    ization
    1.11
    ized
    1.09
    ised
    1.00
    ising
    1.00
    izations
    0.98
    isation
    0.97
    izing
    0.94
    ism
    0.92
    ists
    0.91
    isations
    0.91
    Activations Density 0.053%

    No Known Activations