© 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. 0-RES-JB
    6. 12283
    Prev
    Next
    INDEX
    Explanations

    words related to deconstructing, dismantling, and breaking down structures or systems

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "struct" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     laugh
    -0.81
     lun
    -0.74
     laughter
    -0.66
     Hunt
    -0.64
     gigg
    -0.62
     McGee
    -0.62
     laughing
    -0.62
     royalty
    -0.62
     laughed
    -0.62
     Hancock
    -0.60
    POSITIVE LOGITS
    struct
    4.36
    struction
    2.33
     struct
    2.17
    structed
    2.16
    Struct
    2.07
    STRUCT
    1.93
     Struct
    1.68
    nect
    1.24
    construct
    1.17
    void
    1.11
    Activations Density 0.018%

    No Known Activations