© 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. 1-RES-JB
    11. 20005
    Prev
    Next
    INDEX
    Explanations

    references to the Python programming language

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "Py," indicating references to Python-related products or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesota
    -0.77
    maid
    -0.72
    manship
    -0.70
    ï¸
    -0.70
    IAL
    -0.68
    ously
    -0.65
     Rockefeller
    -0.65
    ________________
    -0.65
    liness
    -0.64
    Relations
    -0.64
    POSITIVE LOGITS
     Py
    1.07
     py
    1.07
    ramids
    1.06
    Py
    1.02
    rites
    0.86
    oleon
    0.86
    ulia
    0.84
    rote
    0.83
    uria
    0.82
    oshenko
    0.78
    Activations Density 0.005%

    No Known Activations