© 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. 0-RES-JB
    11. 8031
    Prev
    Next
    INDEX
    Explanations

    strings that start with special characters such as '(' or '"' and include specific words or patterns afterwards

    oai_token-act-pair · gpt-3.5-turbo

    programming syntax, particularly function calls and print statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Steele
    -0.72
     turf
    -0.62
     Baldwin
    -0.59
     FTA
    -0.56
     Arnold
    -0.55
     Sheridan
    -0.54
     Petersen
    -0.54
     Barcl
    -0.54
    unda
    -0.53
     aisle
    -0.53
    POSITIVE LOGITS
    ("
    3.47
    ('
    3.08
    ($
    2.06
    ().
    1.97
    ({
    1.92
    ([
    1.92
    (&
    1.89
    ();
    1.86
    (-
    1.84
    ((
    1.83
    Activations Density 0.016%

    No Known Activations