© 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. 7-RES-JB
    6. 3805
    Prev
    Next
    INDEX
    Explanations

    sentences indicating surprise or lack thereof

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey a sense of surprise or irony

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cellar
    -0.86
    usha
    -0.80
    apsed
    -0.79
    umin
    -0.78
    alon
    -0.77
     alley
    -0.77
    onde
    -0.76
    interrupted
    -0.75
    allah
    -0.74
    upt
    -0.74
    POSITIVE LOGITS
     Especially
    1.31
     Firstly
    1.29
     Particularly
    1.28
     Universities
    1.24
     Whereas
    1.15
     Suppose
    1.11
     Though
    1.06
     Because
    1.05
     Although
    1.05
     Surely
    1.05
    Activations Density 0.548%

    No Known Activations