© 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. 24401
    Prev
    Next
    INDEX
    Explanations

    phrases expressing personal reactions or experiences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal appreciation and satisfaction

    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
    farious
    -0.69
     violations
    -0.66
     guiName
    -0.63
     breaches
    -0.63
     Occupations
    -0.62
     objections
    -0.61
    etsk
    -0.61
     provocation
    -0.61
    ãĤ¼
    -0.60
     impunity
    -0.59
    POSITIVE LOGITS
     adore
    1.17
     congratulate
    1.09
    'm
    1.09
     hope
    1.08
     love
    1.07
     LOVE
    1.07
     loved
    1.05
     enjoyed
    1.01
     salute
    1.01
     appreciate
    0.99
    Activations Density 0.188%

    No Known Activations