© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 22248
    Prev
    Next
    INDEX
    Explanations

    phrases expressing strong opinions or directives

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express prohibition or restriction

    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
     clears
    -0.73
     restores
    -0.69
     securing
    -0.61
    verified
    -0.61
     restoring
    -0.61
     assures
    -0.60
     Forever
    -0.60
     Fug
    -0.59
     Fine
    -0.57
     Hungry
    -0.57
    POSITIVE LOGITS
     underestimated
    0.99
     underestimate
    0.93
     interfere
    0.91
     worry
    0.87
     bother
    0.87
     confuse
    0.87
     medd
    0.86
     be
    0.86
     rely
    0.85
     burden
    0.84
    Activations Density 0.085%

    No Known Activations