© 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. 11-RES-JB
    11. 9865
    Prev
    Next
    INDEX
    Explanations

    phrases indicating clarity or certainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating clarity or emphasis in statements

    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
    Topics
    -0.70
    soDeliveryDate
    -0.64
     collaborations
    -0.59
     Canaver
    -0.58
    rf
    -0.55
     nets
    -0.55
     stunts
    -0.55
    hov
    -0.54
     halves
    -0.54
     Reincarn
    -0.53
    POSITIVE LOGITS
     abundantly
    1.43
     clear
    1.35
     evident
    1.23
     apparent
    1.21
     obvious
    1.21
     know
    1.13
     known
    1.08
    know
    1.06
     painfully
    1.05
    clear
    1.01
    Activations Density 0.644%

    No Known Activations