© 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. 10-RES-JB
    11. 12752
    Prev
    Next
    INDEX
    Explanations

    user reviews with ratings or scores

    oai_token-act-pair · gpt-3.5-turbo

    ratings and evaluations of products or services

    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
     satir
    -0.91
     enshr
    -0.83
     incentiv
    -0.74
    ulkan
    -0.72
     broadcasting
    -0.69
     schemes
    -0.69
     subter
    -0.69
     combatants
    -0.68
     Confederation
    -0.67
     orche
    -0.67
    POSITIVE LOGITS
    Rated
    1.38
     Bought
    1.11
     Recommend
    1.02
     Purch
    1.01
    Customer
    1.00
     Review
    0.99
    Fit
    0.97
     Rated
    0.96
     Defin
    0.96
    review
    0.93
    Activations Density 0.409%

    No Known Activations