© 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. 18671
    Prev
    Next
    INDEX
    Explanations

    mentions of particular roles that individuals embody or are associated with

    oai_token-act-pair · gpt-3.5-turbo

    references to role models

    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
    yg
    -0.69
     Gleaming
    -0.67
     Oo
    -0.63
     sight
    -0.63
     Trout
    -0.63
     eyeb
    -0.63
    REAM
    -0.62
     Bulg
    -0.62
     Brill
    -0.61
     Uri
    -0.61
    POSITIVE LOGITS
    playing
    1.39
     reversal
    1.03
    played
    0.97
    model
    0.94
     models
    0.90
    plays
    0.90
    players
    0.90
    play
    0.88
    Playing
    0.87
     model
    0.87
    Activations Density 0.039%

    No Known Activations