© 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. 957
    Prev
    Next
    INDEX
    Explanations

    negative statements expressing skepticism or disbelief

    oai_token-act-pair · gpt-3.5-turbo

    negations and assertions about the validity of statements or beliefs

    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
    dule
    -0.70
     photograp
    -0.69
    scene
    -0.68
    quished
    -0.64
    ahime
    -0.63
    ModLoader
    -0.61
    IDs
    -0.60
    prototype
    -0.60
     Kens
    -0.59
     Nanto
    -0.59
    POSITIVE LOGITS
     resonate
    1.32
     apply
    1.10
     prevail
    1.09
     reson
    1.07
     circulate
    1.02
     validity
    0.97
     merit
    0.96
     withstand
    0.93
     persist
    0.93
     prevailed
    0.90
    Activations Density 0.214%

    No Known Activations