© 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. 11155
    Prev
    Next
    INDEX
    Explanations

    years

    oai_token-act-pair · gpt-3.5-turbo

    references to the year 2009

    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
     ancest
    -0.77
    ube
    -0.69
    phy
    -0.62
     sailor
    -0.61
    onite
    -0.60
     toast
    -0.58
    ez
    -0.57
     jelly
    -0.56
    amins
    -0.56
    nces
    -0.55
    POSITIVE LOGITS
    -'
    0.97
    å¹
    0.93
     onwards
    0.81
    ullah
    0.68
    iversary
    0.65
     census
    0.64
    shire
    0.64
     onward
    0.62
    âĢ²
    0.61
    ortal
    0.61
    Activations Density 0.080%

    No Known Activations