© 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. 11-RES-JB
    11. 23922
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Dal" followed by a number depicting the strength of the activation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Dal" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sburgh
    -0.67
    hift
    -0.64
     payday
    -0.64
     rust
    -0.63
     fart
    -0.58
     Arkham
    -0.57
     slack
    -0.57
     pac
    -0.55
     wheelchair
    -0.55
    EED
    -0.55
    POSITIVE LOGITS
    mat
    0.97
    mia
    0.92
    inar
    0.90
    vik
    0.90
    phas
    0.88
    gaard
    0.88
    adier
    0.84
    aran
    0.84
    isco
    0.84
    ouble
    0.82
    Activations Density 0.049%

    No Known Activations