Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 20861
    Prev
    Next
    INDEX
    Explanations

    proper nouns with certain characters and symbols in them

    oai_token-act-pair · gpt-3.5-turbo

    symbols or references to artistic or entertainment mediums, particularly in titles or names

    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
    hement
    -0.71
     Skydragon
    -0.67
     tremend
    -0.62
     Mas
    -0.60
     citiz
    -0.60
     herein
    -0.57
     ren
    -0.52
     naming
    -0.52
    staking
    -0.51
     appeal
    -0.51
    POSITIVE LOGITS
    endant
    0.76
    endants
    0.75
    Iv
    0.73
    gex
    0.71
    flix
    0.70
    ↵
    0.66
    din
    0.65
    edia
    0.64
    ose
    0.64
    athy
    0.64
    Activations Density 0.152%

    No Known Activations