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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4225
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to films or books, especially titles of works

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    titles of works, specifically focusing on the letter 'A' at the beginning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     belts
    -0.77
     annex
    -0.75
     offence
    -0.75
     extent
    -0.74
     amph
    -0.72
     agreements
    -0.71
     upwards
    -0.70
     apex
    -0.70
     autos
    -0.69
     indeed
    -0.68
    POSITIVE LOGITS
     Thousand
    1.04
     Conversation
    1.02
     Gentleman
    1.00
     Fist
    0.98
     Taste
    0.98
    perture
    0.97
    ventus
    0.96
     Tale
    0.96
     Beautiful
    0.95
     Subtle
    0.95
    Activations Density 0.057%

    No Known Activations