© 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. 10-RES-JB
    11. 8569
    Prev
    Next
    INDEX
    Explanations

    proper nouns or entities related to company names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of companies or organizations

    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
     distingu
    -0.70
     flare
    -0.66
     thous
    -0.66
     circumst
    -0.65
    */(
    -0.64
     swast
    -0.63
     constitu
    -0.63
     appendix
    -0.62
     pont
    -0.62
    xual
    -0.61
    POSITIVE LOGITS
     Creek
    0.83
    Works
    0.81
    Sense
    0.79
     Labs
    0.79
     Artists
    0.77
     Oaks
    0.77
    pedia
    0.76
     Records
    0.75
    Pure
    0.74
    Quest
    0.74
    Activations Density 0.195%

    No Known Activations