© 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. 22224
    Prev
    Next
    INDEX
    Explanations

    words related to production or creation

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of creating or generating items or outcomes

    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
    agall
    -0.74
    Card
    -0.65
    quest
    -0.63
     Brow
    -0.63
    LESS
    -0.63
    Safe
    -0.62
    Charg
    -0.62
    bull
    -0.62
    Nap
    -0.61
    neck
    -0.61
    POSITIVE LOGITS
     produce
    3.42
     Produ
    2.10
     produces
    2.09
    produ
    2.08
     producing
    1.90
     produced
    1.75
     generate
    1.55
     produ
    1.53
     yield
    1.53
     reproduce
    1.50
    Activations Density 0.017%

    No Known Activations