© 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. 6-RES-JB
    11. 22916
    Prev
    Next
    INDEX
    Explanations

    words indicating specific relationships or connections, such as "when", "and", and "by"

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and transition words indicating relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     photoc
    -0.68
    assetsadobe
    -0.66
     [];
    -0.66
     behav
    -0.64
     acron
    -0.63
     ESP
    -0.62
     SAN
    -0.62
     DeL
    -0.61
     horizont
    -0.61
     microphones
    -0.60
    POSITIVE LOGITS
    roth
    0.96
    raq
    0.96
    zon
    0.93
    mac
    0.92
    kin
    0.91
    yx
    0.88
    aris
    0.88
    roy
    0.87
    nard
    0.87
    fur
    0.86
    Activations Density 0.340%

    No Known Activations