© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 18841
    Prev
    Next
    INDEX
    Explanations

    negative statements where the subject doesn't understand, recommend, like, know, have, or feel comfortable

    oai_token-act-pair · gpt-3.5-turbo

    negative or dismissive phrases indicating disbelief or lack of understanding

    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
    ãĤ¶
    -0.94
    NetMessage
    -0.80
    once
    -0.76
    Reader
    -0.73
    unless
    -0.72
    æ©Ł
    -0.71
    emonium
    -0.71
    []
    -0.70
    ãĤ¤ãĥĪ
    -0.68
    ĸļ
    -0.68
    POSITIVE LOGITS
     already
    1.14
     comply
    0.86
     careful
    0.85
     resolve
    0.83
     agree
    0.81
     satisf
    0.81
     sufficiently
    0.80
     succeed
    0.80
     cooperate
    0.76
     suffice
    0.75
    Activations Density 0.097%

    No Known Activations