© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14100
    Prev
    Next
    INDEX
    Explanations

    strings related to programming and coding, particularly involving characters and data types

    oai_token-act-pair · gpt-3.5-turbo

    programming terminology related to strings and character data types

    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
    ),"
    -0.75
     Dund
    -0.68
     psychiat
    -0.65
     tatt
    -0.62
    :[
    -0.60
     Urug
    -0.60
    kil
    -0.59
    ."[
    -0.59
    ��
    -0.58
    bleacher
    -0.58
    POSITIVE LOGITS
     >
    2.68
    >
    2.43
    >)
    2.08
    >,
    2.06
    >.
    1.98
    >"
    1.97
     >>
    1.89
    _>
    1.82
     ><
    1.82
    >[
    1.81
    Activations Density 0.066%

    No Known Activations