© 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. 8583
    Prev
    Next
    INDEX
    Explanations

    phrases indicating repetition or frequency

    oai_token-act-pair · gpt-3.5-turbo

    references to recurring events or concepts

    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
    DX
    -0.63
    rooms
    -0.60
    rawdownloadcloneembedreportprint
    -0.59
     salaries
    -0.55
     lifestyles
    -0.55
     NI
    -0.54
     exports
    -0.54
     SX
    -0.54
    EX
    -0.52
     Rings
    -0.51
    POSITIVE LOGITS
     imaginable
    0.77
     penny
    0.73
    Else
    0.69
    minute
    0.69
    chance
    0.68
     minute
    0.67
     conceivable
    0.66
    thens
    0.65
     dime
    0.65
    adelphia
    0.65
    Activations Density 0.052%

    No Known Activations