© 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. 0-RES-JB
    11. 19859
    Prev
    Next
    INDEX
    Explanations

    words related to filling or completion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "filling" in various contexts

    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
    MIT
    -0.87
    antis
    -0.82
    mart
    -0.68
    NK
    -0.66
    TD
    -0.66
    orem
    -0.64
     Leap
    -0.64
    imar
    -0.63
    utan
    -0.63
    mit
    -0.62
    POSITIVE LOGITS
     filling
    3.58
     fill
    2.10
     fills
    1.83
     filled
    1.63
     Fill
    1.63
     stuffing
    1.62
     topping
    1.51
    fill
    1.48
     filler
    1.45
    Fill
    1.43
    Activations Density 0.017%

    No Known Activations