© 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. 23544
    Prev
    Next
    INDEX
    Explanations

    words related to emotions or actions emphasizing a sense of intensity or importance

    oai_token-act-pair · gpt-3.5-turbo

    words related to different forms of the word "enemies" or expressions of opposition

    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
    yip
    -0.77
    apest
    -0.75
    é¾įå
    -0.75
    jri
    -0.73
    cules
    -0.62
    ancial
    -0.60
     incon
    -0.60
    appropriate
    -0.59
    hops
    -0.58
    swick
    -0.57
    POSITIVE LOGITS
    ciating
    1.08
    achment
    0.98
    enment
    0.89
    ãĤ¨ãĥ«
    0.75
    emy
    0.73
    ĸļ
    0.73
    yll
    0.67
    iasm
    0.67
    emies
    0.65
    ached
    0.64
    Activations Density 0.065%

    No Known Activations