© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5175
    Prev
    Next
    INDEX
    Explanations

    terms related to adding, withdrawing, or specifying amounts in a process flow

    oai_token-act-pair · gpt-3.5-turbo
    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
    aughs
    -0.70
    Laughs
    -0.67
    andi
    -0.64
    wives
    -0.63
    ihilation
    -0.63
    illions
    -0.62
     enormously
    -0.62
    comings
    -0.61
     CEOs
    -0.61
    cking
    -0.61
    POSITIVE LOGITS
     your
    1.23
    your
    1.04
     you
    1.00
     YOUR
    0.98
     yours
    0.94
    Your
    0.93
     Your
    0.92
     desired
    0.88
     specified
    0.85
    you
    0.78
    Activations Density 0.345%

    No Known Activations