© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 4125
    Prev
    Next
    INDEX
    Explanations

    references to medical or scientific terms related to specific bodily functions or conditions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the token "op"

    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
     Lauder
    -0.69
     intending
    -0.64
     FANT
    -0.63
     Gateway
    -0.62
    ãĤĭ
    -0.59
     Sins
    -0.59
     Bond
    -0.59
     wells
    -0.58
    IGHTS
    -0.57
     devils
    -0.57
    POSITIVE LOGITS
    inion
    1.34
    yright
    1.33
    sych
    1.31
    olitan
    1.31
    lication
    1.23
    edia
    1.16
    rodu
    1.15
    rompt
    1.12
    rano
    1.12
    ocalypse
    1.11
    Activations Density 0.028%

    No Known Activations