© 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. 2-RES-JB
    11. 19124
    Prev
    Next
    INDEX
    Explanations

    numbers representing a quantity of items or a specific count

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number "10."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStream
    -0.76
    netflix
    -0.76
    TextColor
    -0.74
    atem
    -0.72
    rely
    -0.69
    hammad
    -0.67
    unct
    -0.66
    rette
    -0.65
    isoft
    -0.64
     tradem
    -0.64
    POSITIVE LOGITS
    %"
    0.96
    84
    0.91
    85
    0.90
    92
    0.90
    81
    0.90
    th
    0.90
    600
    0.89
    82
    0.89
    400
    0.87
    ^{
    0.87
    Activations Density 0.048%

    No Known Activations