© 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. 7766
    Prev
    Next
    INDEX
    Explanations

    words related to transactions, possessions, and acquisitions

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and items related to supplies or resources

    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
    hower
    -0.87
    ĸļ
    -0.75
    uckland
    -0.70
    imester
    -0.69
    igmatic
    -0.68
    ģĸ
    -0.67
    KEN
    -0.66
    é¾įå¥ij士
    -0.66
    Tip
    -0.66
    ç·
    -0.66
    POSITIVE LOGITS
     minerals
    1.11
     belongings
    1.07
     tissues
    1.07
     nutrients
    1.04
     beverages
    0.99
     herbs
    0.98
     accessories
    0.98
     resources
    0.96
     chemicals
    0.95
     fluids
    0.95
    Activations Density 0.382%

    No Known Activations