© 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. 1-RES-JB
    6. 13158
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computers or software including the number "7"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number seven in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActiveUn
    -0.76
    assetsadobe
    -0.71
    gart
    -0.69
     nomine
    -0.67
     pastoral
    -0.67
    olate
    -0.66
     Leban
    -0.66
     yield
    -0.66
     friction
    -0.66
     prose
    -0.65
    POSITIVE LOGITS
    07
    1.02
    ecause
    1.00
    69
    0.99
    88
    0.96
    87
    0.90
    49
    0.90
    ï¸ı
    0.90
    46
    0.90
    06
    0.89
    67
    0.89
    Activations Density 0.051%

    No Known Activations