© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 22160
    Prev
    Next
    INDEX
    Explanations

    links instructing users to click for further information or action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" and its variations, indicating directives or calls to action

    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
    existent
    -0.73
    quickShipAvailable
    -0.70
     Kinnikuman
    -0.63
    existence
    -0.63
    ELD
    -0.61
    offensive
    -0.58
     ][
    -0.56
    tein
    -0.56
    furt
    -0.55
     Mechdragon
    -0.55
    POSITIVE LOGITS
     learn
    1.39
     download
    1.22
     browse
    1.20
     subscribe
    1.17
     see
    1.16
     find
    1.14
     receive
    1.13
     submit
    1.12
     navigate
    1.11
     discover
    1.10
    Activations Density 0.083%

    No Known Activations