© 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. 0-RES-JB
    11. 8378
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "drew" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "drew" and its variations

    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
    elia
    -0.64
     recovery
    -0.60
    ible
    -0.59
     Enterprise
    -0.58
     Messages
    -0.58
     mobility
    -0.58
     redundancy
    -0.57
     PM
    -0.57
     BA
    -0.56
     Recovery
    -0.56
    POSITIVE LOGITS
     drew
    3.42
     draws
    2.28
     draw
    1.99
     drawing
    1.68
     drawn
    1.64
     Draw
    1.64
    Draw
    1.60
     Drawn
    1.57
     Drawing
    1.52
     attracted
    1.45
    Activations Density 0.016%

    No Known Activations