© 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. 13759
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to organizations, events, and positions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to organizations or institutions

    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
     pend
    -0.74
     oneself
    -0.72
     guessed
    -0.68
     nerv
    -0.68
     sorcerer
    -0.68
    awaru
    -0.67
     compan
    -0.67
     ib
    -0.67
     ay
    -0.66
     porous
    -0.65
    POSITIVE LOGITS
     Edition
    1.09
     Responsibility
    1.09
     Series
    1.05
     Preview
    1.00
     Facility
    1.00
     Course
    0.99
     Crimes
    0.99
     Guide
    0.98
     Program
    0.98
     Rounds
    0.97
    Activations Density 0.332%

    No Known Activations