© 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. 10983
    Prev
    Next
    INDEX
    Explanations

    numerical measurements like weights, dimensions, and distances

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to weights 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
    activate
    -0.74
    imore
    -0.70
    isky
    -0.69
    arling
    -0.65
    illon
    -0.65
    versions
    -0.65
    activated
    -0.64
    liction
    -0.63
    edient
    -0.63
    activation
    -0.63
    POSITIVE LOGITS
    ½
    0.94
     centimeters
    0.94
    cm
    0.91
    192
    0.90
    75
    0.90
    80
    0.86
    200
    0.85
    9999
    0.84
    %;
    0.83
    500
    0.83
    Activations Density 0.169%

    No Known Activations