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. 19734
    Prev
    Next
    INDEX
    Explanations

    terms related to regrouping or regathering

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "regress," indicating a focus on themes of regression or decline

    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
    hower
    -0.80
    terday
    -0.80
     disapproval
    -0.69
     perfect
    -0.68
     Apostle
    -0.66
    lihood
    -0.66
    WARE
    -0.64
    enegger
    -0.64
     deduction
    -0.63
    Fine
    -0.63
    POSITIVE LOGITS
    roup
    1.71
    ressive
    1.54
    imens
    1.44
    gae
    1.40
    roups
    1.39
    rowth
    1.32
    aining
    1.28
    urg
    1.26
    ressed
    1.24
    iments
    1.22
    Activations Density 0.020%

    No Known Activations