© 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. 20568
    Prev
    Next
    INDEX
    Explanations

    expressions describing personal experiences or accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    expressions of significant personal experiences and emotions

    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
    pmwiki
    -0.91
    krit
    -0.78
     dispute
    -0.77
     inconsist
    -0.75
     derog
    -0.72
    Dialog
    -0.70
     defic
    -0.69
     plaus
    -0.69
     disputes
    -0.68
    farious
    -0.68
    POSITIVE LOGITS
    Seeing
    1.09
     witnessing
    1.09
     seeing
    1.04
     Seeing
    1.03
     watching
    1.03
     cheering
    1.02
     Watching
    0.98
     THANK
    0.98
     knowing
    0.97
    watching
    0.95
    Activations Density 0.426%

    No Known Activations