© 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. 3-RES-JB
    11. 9306
    Prev
    Next
    INDEX
    Explanations

    numerical values formatted as dates (e.g., month-day-year) in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical values, especially ratings or counts related to votes or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atis
    -0.94
    akespe
    -0.86
    atics
    -0.86
    abwe
    -0.85
    ramid
    -0.84
    redit
    -0.82
    retched
    -0.80
    akens
    -0.75
    ourge
    -0.74
    ategory
    -0.72
    POSITIVE LOGITS
    00
    0.86
    vier
    0.75
    st
    0.74
    ¯¯
    0.73
    rd
    0.73
     msec
    0.71
    50
    0.71
    30
    0.71
    nm
    0.69
    803
    0.68
    Activations Density 0.016%

    No Known Activations