© 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. 11-RES-JB
    11. 17395
    Prev
    Next
    INDEX
    Explanations

    dates written in the format of the day followed by the month

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number 12 in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osphere
    -0.69
    icipated
    -0.68
    ersen
    -0.65
    ique
    -0.63
    ause
    -0.59
    iques
    -0.59
    ically
    -0.59
    Ô
    -0.59
    icist
    -0.58
    ierrez
    -0.58
    POSITIVE LOGITS
    noon
    1.11
    03
    1.08
    02
    1.08
    04
    1.07
    05
    1.04
    06
    1.04
    07
    1.02
    09
    1.00
    650
    0.96
    50
    0.94
    Activations Density 0.097%

    No Known Activations