© 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. 18700
    Prev
    Next
    INDEX
    Explanations

    instances of time-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    tentative language or uncertainty 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
    Synopsis
    -0.79
    bg
    -0.70
    çĦ
    -0.70
    icipated
    -0.69
    gemony
    -0.68
    èª
    -0.68
    åĽ
    -0.66
    irtual
    -0.63
    uments
    -0.63
    endish
    -0.61
    POSITIVE LOGITS
     fifteen
    1.19
     fifty
    1.19
     thirty
    1.12
     eighty
    1.11
     sixty
    1.11
     twelve
    1.10
     seventy
    1.09
     50
    1.08
     twenty
    1.07
     five
    1.07
    Activations Density 0.328%

    No Known Activations