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. 11-RES-JB
    6. 10347
    Prev
    Next
    INDEX
    Explanations

    personal information about various individuals, such as birthdates, occupations, and nationality

    oai_token-act-pair · gpt-3.5-turbo

    individuals' names and their associated backgrounds or professions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CONCLUS
    -0.89
    ctory
    -0.68
     Saying
    -0.67
     reversal
    -0.65
     inaction
    -0.62
     dstg
    -0.61
     insensitive
    -0.61
     silence
    -0.60
     forgetting
    -0.60
    forcement
    -0.59
    POSITIVE LOGITS
     graduated
    1.25
     specializes
    1.19
     lived
    1.14
     grew
    1.12
     resided
    1.11
     founded
    1.10
     embodies
    1.09
     belonged
    1.08
     resides
    1.07
     originated
    1.05
    Activations Density 0.386%

    No Known Activations