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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 4788
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the opposite of something happening or being necessary

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "will not be."

    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
    arently
    -0.68
    rather
    -0.67
    strous
    -0.65
    prototype
    -0.62
    NYSE
    -0.60
     Allaah
    -0.58
    probably
    -0.58
    sometimes
    -0.58
    culosis
    -0.57
    cius
    -0.57
    POSITIVE LOGITS
     able
    1.26
     tolerated
    1.16
     anymore
    0.97
     anywhere
    0.89
     swayed
    0.88
     enough
    0.87
     dissu
    0.86
     allowed
    0.85
     intimidated
    0.84
     bothered
    0.83
    Activations Density 0.100%

    No Known Activations