© 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. 3-RES-JB
    11. 6305
    Prev
    Next
    INDEX
    Explanations

    action verbs related to methods or approaches

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest methods or approaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DAQ
    -0.79
    lvl
    -0.77
    CHAT
    -0.74
    Merit
    -0.74
    ANC
    -0.70
    ancies
    -0.69
    Lyn
    -0.68
    QL
    -0.68
    Alert
    -0.67
     Issues
    -0.66
    POSITIVE LOGITS
     derog
    0.82
     shortcut
    0.72
    ortium
    0.71
     efficiently
    0.70
     workaround
    0.70
    undo
    0.69
     structured
    0.69
     approach
    0.69
     indirect
    0.69
     interpreting
    0.68
    Activations Density 0.219%

    No Known Activations