© 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. 20496
    Prev
    Next
    INDEX
    Explanations

    strings related to computer programming and code implementation

    oai_token-act-pair · gpt-3.5-turbo

    code snippets and programming-related syntax

    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
     museums
    -0.79
     moderates
    -0.76
     fetish
    -0.70
     incentiv
    -0.69
     mosques
    -0.69
     bloggers
    -0.69
    ilitarian
    -0.68
    urat
    -0.67
     gardens
    -0.66
     photographers
    -0.66
    POSITIVE LOGITS
     Finished
    1.28
     %
    1.23
    ERROR
    1.21
     "%
    1.16
    Hello
    1.13
    Result
    1.11
     ERROR
    1.11
    Error
    1.10
    Output
    1.10
    %-
    1.08
    Activations Density 0.112%

    No Known Activations