© 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. 7859
    Prev
    Next
    INDEX
    Explanations

    words related to strong positive qualities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    key concepts related to societal and economic structures

    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
    tnc
    -0.77
    earances
    -0.70
    respect
    -0.68
    cffff
    -0.67
    CRIP
    -0.65
    ãĥīãĥ©
    -0.65
    certain
    -0.63
    alyses
    -0.63
    such
    -0.62
    adoes
    -0.61
    POSITIVE LOGITS
    liest
    1.67
    iest
    1.54
     equivalent
    1.22
    hest
    1.16
     centerpiece
    1.07
    most
    1.01
     closest
    0.96
    ultimate
    0.94
    est
    0.93
     smartest
    0.91
    Activations Density 0.488%

    No Known Activations