© 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. 9-RES-JB
    11. 7476
    Prev
    Next
    INDEX
    Explanations

    photo credits within text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of elements from a structured content format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ixel
    -0.73
     compulsion
    -0.69
     continents
    -0.69
    voy
    -0.68
    bats
    -0.68
    iqu
    -0.67
    staking
    -0.65
     ensl
    -0.65
    hered
    -0.64
    lain
    -0.64
    POSITIVE LOGITS
     COURT
    1.14
     Courtesy
    1.12
     ©
    1.03
     Associated
    0.98
     Provided
    0.97
     Getty
    0.96
     REUTERS
    0.89
     JOHN
    0.87
    Associated
    0.86
     Supp
    0.85
    Activations Density 0.028%

    No Known Activations