© 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. 7-RES-JB
    6. 8914
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terms related to engineering, construction, and chemistry

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to scientific processes and measurements

    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
    partisan
    -0.85
    isode
    -0.76
    atform
    -0.65
    ifax
    -0.62
    intend
    -0.60
     Sutherland
    -0.59
    conservative
    -0.58
     Scal
    -0.58
     Sinclair
    -0.56
     Rosenstein
    -0.56
    POSITIVE LOGITS
     guiActiveUn
    0.65
    ãĤ©
    0.64
    ifice
    0.57
     prest
    0.57
     [|
    0.57
    eering
    0.57
    ItemImage
    0.56
     Âł Âł Âł Âł Âł Âł Âł Âł
    0.54
    ³³³³
    0.53
    romeda
    0.53
    Activations Density 1.176%

    No Known Activations