© 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. 10-RES-JB
    11. 2855
    Prev
    Next
    INDEX
    Explanations

    programming code snippets containing specific variable assignments

    oai_token-act-pair · gpt-3.5-turbo

    code snippets or programming syntax, particularly involving variable assignments and function calls

    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
     Sorce
    -0.72
     Cooke
    -0.70
     mechanisms
    -0.67
     Goddard
    -0.65
    idelines
    -0.63
     relics
    -0.63
     Chambers
    -0.63
     Mechan
    -0.62
     spons
    -0.61
     antioxid
    -0.61
    POSITIVE LOGITS
    foo
    1.57
     foo
    1.44
    hello
    1.33
    abc
    1.19
     Foo
    1.15
    ([
    1.14
    Hello
    1.12
     {:
    1.11
     ['
    1.08
     hello
    1.08
    Activations Density 0.129%

    No Known Activations