© 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. 11-RES-JB
    11. 18517
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific names or titles

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bean
    -0.94
     Schwe
    -0.83
     GF
    -0.83
     bean
    -0.81
     Progressive
    -0.79
     Chloe
    -0.78
     bould
    -0.77
     Powell
    -0.77
     Warren
    -0.76
     Albany
    -0.76
    POSITIVE LOGITS
    ir
    2.04
    IR
    1.74
    Ir
    1.60
     IR
    1.56
    iris
    1.53
     ir
    1.46
     Ir
    1.46
    ire
    1.44
    irs
    1.39
    iri
    1.38
    Activations Density 0.271%

    No Known Activations