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. 7346
    Prev
    Next
    INDEX
    Explanations

    sentences with a period followed by a numeric code

    oai_token-act-pair · gpt-3.5-turbo

    the presence of legal or judicial outcomes

    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
     foc
    -0.79
     expansions
    -0.77
     stadiums
    -0.76
     languages
    -0.76
     synerg
    -0.76
     grouped
    -0.75
     nuts
    -0.75
     deflation
    -0.75
     spears
    -0.75
     dotted
    -0.74
    POSITIVE LOGITS
    Christopher
    1.35
    Jason
    1.35
    Daniel
    1.31
    Edward
    1.31
    Joshua
    1.31
    Joseph
    1.30
    Michael
    1.30
    Charles
    1.30
    Matthew
    1.29
    William
    1.26
    Activations Density 0.173%

    No Known Activations