© 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. 10-RES-JB
    6. 812
    Prev
    Next
    INDEX
    Explanations

    words containing the prefix "re-" with a variety of actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to actions involving redoing, repurposing, or misusing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NESS
    -0.72
     entrepreneurship
    -0.69
    lihood
    -0.69
     Anger
    -0.68
     arrogance
    -0.68
     similarity
    -0.66
     divergence
    -0.65
     seriousness
    -0.65
     sincerity
    -0.65
     resemblance
    -0.65
    POSITIVE LOGITS
    ased
    1.40
    urated
    1.38
    rolled
    1.35
    arthed
    1.33
    idden
    1.32
    opped
    1.31
    ised
    1.31
    oned
    1.30
    idered
    1.30
    itored
    1.29
    Activations Density 0.233%

    No Known Activations