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

    Neuronpedia

    APICircuit 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. 21022
    Prev
    Next
    INDEX
    Explanations

    percentage values

    oai_token-act-pair · gpt-3.5-turbo

    percentages or statistical data related to rarity

    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
     tranquil
    -0.68
     tyrann
    -0.64
     compassionate
    -0.62
     recons
    -0.62
     Jem
    -0.61
     scrambled
    -0.61
     indebted
    -0.60
     coun
    -0.60
     nour
    -0.60
     resent
    -0.59
    POSITIVE LOGITS
     Discuss
    0.87
     ABV
    0.82
     Overall
    0.79
    ooter
    0.77
    ooters
    0.76
     Unsure
    0.76
     Percentage
    0.76
    ername
    0.73
    vantage
    0.72
    Percent
    0.72
    Activations Density 0.033%

    No Known Activations