© 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. 3698
    Prev
    Next
    INDEX
    Explanations

    quotations within text

    oai_token-act-pair · gpt-3.5-turbo

    instances of dialogue or quotes within the text

    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
     encl
    -0.77
     upstream
    -0.69
     prolifer
    -0.69
     subsidized
    -0.68
     disinformation
    -0.68
     federally
    -0.67
     popul
    -0.67
     subsidies
    -0.67
    Ń·
    -0.67
     parap
    -0.66
    POSITIVE LOGITS
    Yeah
    1.12
    Obviously
    1.08
    Coach
    1.03
    Whoever
    0.99
    Honestly
    0.98
    Everybody
    0.98
    Absolutely
    0.98
    BuyableInstoreAndOnline
    0.98
    We
    0.97
    Very
    0.94
    Activations Density 0.110%

    No Known Activations