© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 762
    Prev
    Next
    INDEX
    Explanations

    statements from various individuals

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks and speech citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bean
    -0.87
     tack
    -0.80
     censored
    -0.80
     plaus
    -0.78
     complain
    -0.77
     spill
    -0.77
     asshole
    -0.76
     blame
    -0.76
     disapprove
    -0.75
     fodder
    -0.73
    POSITIVE LOGITS
    Our
    1.57
    We
    1.47
    Today
    1.39
    Working
    1.37
    Having
    1.37
    This
    1.34
    Firstly
    1.32
    Congratulations
    1.32
    Throughout
    1.29
    Following
    1.26
    Activations Density 0.146%

    No Known Activations