© 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. 10-RES-JB
    11. 16099
    Prev
    Next
    INDEX
    Explanations

    years or dates

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years or time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snipp
    -0.62
     Wem
    -0.56
    imore
    -0.54
     Pru
    -0.53
    Jackson
    -0.52
    Pack
    -0.52
     dy
    -0.51
    umbn
    -0.51
    ashtra
    -0.51
     Dil
    -0.50
    POSITIVE LOGITS
     onwards
    1.00
     onward
    0.89
    âĢ²
    0.79
     inception
    0.73
    when
    0.71
    -'
    0.67
    iatus
    0.64
    quist
    0.62
    staking
    0.60
    .
    0.60
    Activations Density 0.095%

    No Known Activations