© 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. 525
    Prev
    Next
    INDEX
    Explanations

    phrases related to learning and knowledge acquisition

    oai_token-act-pair · gpt-3.5-turbo

    references to relationships and their dynamics, particularly involving people and communities

    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
    ãĤ´ãĥ³
    -0.95
    BuyableInstoreAndOnline
    -0.85
     lamented
    -0.69
    wang
    -0.69
    Released
    -0.69
     penned
    -0.68
     Released
    -0.66
     ®
    -0.66
    ccording
    -0.65
     partName
    -0.64
    POSITIVE LOGITS
     somebody
    1.52
     everybody
    1.50
     [
    1.35
     anybody
    1.27
     ['
    1.21
     stuff
    1.11
     us
    1.02
     things
    0.98
     ourselves
    0.97
     everything
    0.96
    Activations Density 0.774%

    No Known Activations