© 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. 10-RES-JB
    11. 10033
    Prev
    Next
    INDEX
    Explanations

    negative statements containing the word "not"

    oai_token-act-pair · gpt-3.5-turbo

    negations or denials of existence or relevance

    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
    Vers
    -0.68
     Unfortunately
    -0.62
    Unfortunately
    -0.59
    Less
    -0.59
     Sadly
    -0.58
    Tor
    -0.55
    utt
    -0.55
    essim
    -0.55
     Less
    -0.54
    aughs
    -0.53
    POSITIVE LOGITS
     nor
    0.90
     even
    0.90
     anywhere
    0.88
     anybody
    0.85
     whatsoever
    0.82
     remotely
    0.81
     anything
    0.80
     ever
    0.78
     anyone
    0.78
    anything
    0.77
    Activations Density 0.358%

    No Known Activations