© 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. 10-RES-JB
    11. 2679
    Prev
    Next
    INDEX
    Explanations

    double hyphens

    oai_token-act-pair · gpt-3.5-turbo

    instances of pauses, interruptions, or filler expressions in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Citiz
    -0.76
     REUTERS
    -0.61
     Zup
    -0.60
    ãĤ°
    -0.58
     Pearce
    -0.58
    osate
    -0.57
     Angelo
    -0.56
    amsung
    -0.56
    clusively
    -0.56
    ORTS
    -0.56
    POSITIVE LOGITS
     uh
    1.33
    yeah
    1.25
     um
    1.16
    fuck
    1.15
    wow
    1.11
     yeah
    1.11
    well
    1.09
    wait
    1.08
    you
    1.07
     wow
    1.01
    Activations Density 0.124%

    No Known Activations