© 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. 7-RES-JB
    11. 23030
    Prev
    Next
    INDEX
    Explanations

    specific letters or symbols in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to group classifications or standings, particularly in competitive contexts

    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
    href
    -0.72
    pool
    -0.68
    owe
    -0.67
    Ay
    -0.66
    bats
    -0.65
    lore
    -0.65
    vim
    -0.65
    archive
    -0.65
    ãĥ´
    -0.65
    hn
    -0.65
    POSITIVE LOGITS
    verages
    1.06
     guiActiveUnfocused
    0.78
    itialized
    0.74
     guiName
    0.73
    ioxide
    0.71
     Skydragon
    0.70
    +.
    0.65
     subdiv
    0.64
     metab
    0.63
    cknow
    0.63
    Activations Density 0.125%

    No Known Activations