© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 5646
    Prev
    Next
    INDEX
    Explanations

    the term "sm" with varying degrees of intensity

    oai_token-act-pair · gpt-3.5-turbo

    words that start with "sm"

    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
     Revival
    -0.68
     pleas
    -0.63
    EMENT
    -0.61
     marked
    -0.60
     trained
    -0.58
     Sym
    -0.58
     chang
    -0.58
     quarters
    -0.57
     generals
    -0.56
     performing
    -0.56
    POSITIVE LOGITS
    oky
    1.39
    eared
    1.36
    itten
    1.31
    attering
    1.31
    udging
    1.27
    udge
    1.24
    elly
    1.24
    okin
    1.24
    earing
    1.14
    acking
    1.14
    Activations Density 0.015%

    No Known Activations