© 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. 7-RES-JB
    11. 1472
    Prev
    Next
    INDEX
    Explanations

    numerical figures and quantities

    oai_token-act-pair · gpt-3.5-turbo

    quantifiable metrics and measures in financial and economic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     directions
    -0.68
     calendars
    -0.64
     recommendations
    -0.59
     dating
    -0.58
     cancell
    -0.57
     pronounce
    -0.56
     provocation
    -0.56
     lyrics
    -0.55
     moving
    -0.55
     liabilities
    -0.55
    POSITIVE LOGITS
    dozen
    1.17
    undreds
    1.10
    few
    1.03
     dozen
    0.97
    orically
    0.90
     handful
    0.89
    ouple
    0.88
    thirds
    0.87
     majority
    0.83
    ousands
    0.82
    Activations Density 0.658%

    No Known Activations