© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7879
    Prev
    Next
    INDEX
    Explanations

    verbs that describe actions or states

    oai_token-act-pair · gpt-3.5-turbo

    verbs suggesting explanations or descriptions of actions

    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
    selves
    -0.82
     selves
    -0.66
    FL
    -0.62
    mint
    -0.61
    Copyright
    -0.61
     millenn
    -0.59
    illion
    -0.58
    halla
    -0.58
    aroo
    -0.57
    istani
    -0.57
    POSITIVE LOGITS
     herself
    1.21
     himself
    1.07
     her
    0.87
     his
    0.87
     Himself
    0.85
     hers
    0.79
     Chess
    0.60
    âĦ¢:
    0.60
    his
    0.59
     Boh
    0.58
    Activations Density 0.474%

    No Known Activations