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. 7351
    Prev
    Next
    INDEX
    Explanations

    phrases indicating determination or perseverance

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "no matter" indicating a sense of inevitability or disregard for circumstances

    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
    uctions
    -0.69
    oute
    -0.67
    eg
    -0.63
    iens
    -0.62
    BSD
    -0.61
     Missile
    -0.60
    uction
    -0.60
    ISS
    -0.60
    issance
    -0.60
    agues
    -0.59
    POSITIVE LOGITS
     how
    1.45
    how
    1.21
     what
    1.17
     HOW
    1.15
     whether
    1.09
    what
    1.06
     WHAT
    1.05
     whatsoever
    0.91
     where
    0.90
    whether
    0.88
    Activations Density 0.021%

    No Known Activations