© 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. 9-RES-JB
    6. 4335
    Prev
    Next
    INDEX
    Explanations

    dates of events

    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
    iously
    -0.77
    onic
    -0.75
    izing
    -0.74
    amn
    -0.73
    agic
    -0.73
    ious
    -0.69
    lass
    -0.67
    meal
    -0.66
    ongh
    -0.66
    ongs
    -0.65
    POSITIVE LOGITS
    å¹
    0.98
     onwards
    0.98
    â̳
    0.76
     Edition
    0.75
     EDITION
    0.74
     Exhibition
    0.73
    20439
    0.70
     onward
    0.68
    è¦ļéĨĴ
    0.68
     Nobel
    0.68
    Activations Density 0.063%

    No Known Activations