© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 4221
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and digital services

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.76
    reditary
    -0.73
    nen
    -0.73
     Rebell
    -0.70
     Marketable
    -0.69
    estinal
    -0.67
     Triangle
    -0.66
    rious
    -0.63
     Forsaken
    -0.63
     [|
    -0.63
    POSITIVE LOGITS
    rencies
    0.97
    apps
    0.85
     providers
    0.85
     provider
    0.82
     apps
    0.78
    annels
    0.78
     platforms
    0.77
    devices
    0.77
    Apps
    0.76
     Apps
    0.75
    Activations Density 0.311%

    No Known Activations