© 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. 15703
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical information

    oai_token-act-pair · gpt-3.5-turbo

    verbs that indicate changes or trends in various contexts

    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
     Offer
    -0.79
     Penal
    -0.72
     Place
    -0.68
     attribution
    -0.64
     Deliver
    -0.63
     discard
    -0.63
     recalls
    -0.62
     pronounce
    -0.62
     hears
    -0.61
     Commun
    -0.59
    POSITIVE LOGITS
     risen
    1.63
     plummeted
    1.55
     soared
    1.50
     surged
    1.41
     skyrocket
    1.39
     fallen
    1.36
     tripled
    1.32
     decreased
    1.31
     climbed
    1.29
     dwind
    1.29
    Activations Density 0.073%

    No Known Activations