© 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. 8-RES-JB
    11. 6190
    Prev
    Next
    INDEX
    Explanations

    data types and programming-related keywords

    oai_token-act-pair · gpt-3.5-turbo

    programming-related structures and types, particularly in C++ syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gaard
    -1.08
    bots
    -0.91
    avers
    -0.82
    OHN
    -0.81
    gard
    -0.80
    doms
    -0.80
    laws
    -0.78
    grain
    -0.78
    urers
    -0.77
    mast
    -0.77
    POSITIVE LOGITS
    []
    1.00
     (*
    0.89
    ptr
    0.84
     []
    0.81
     integer
    0.74
    acters
    0.72
    Ptr
    0.72
     sizing
    0.69
     size
    0.69
     Scal
    0.68
    Activations Density 0.035%

    No Known Activations