© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 23995
    Prev
    Next
    INDEX
    Explanations

    texts related to product listings or items for sale

    oai_token-act-pair · gpt-3.5-turbo

    items related to various products or equipment, particularly those with pricing or characteristics for purchase

    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
     organis
    -0.98
     decisions
    -0.84
     strateg
    -0.84
     footing
    -0.84
     advis
    -0.83
     judgement
    -0.82
     declarations
    -0.79
     hust
    -0.79
     elector
    -0.78
     absentee
    -0.77
    POSITIVE LOGITS
    Premium
    1.10
    Dual
    1.09
    Female
    0.95
    Includes
    0.94
     Enhance
    0.94
    optional
    0.93
     Featuring
    0.93
    Increases
    0.92
     Includes
    0.92
    Perfect
    0.91
    Activations Density 0.276%

    No Known Activations