© 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. 13804
    Prev
    Next
    INDEX
    Explanations

    phrases related to the complexity, diversity, and scale of various subjects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the characteristics and intricacies of various subjects

    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
    oras
    -0.71
    alus
    -0.62
    inis
    -0.60
    eg
    -0.60
    itionally
    -0.59
    xiety
    -0.59
     newsletters
    -0.56
    EMS
    -0.56
    bye
    -0.55
    idav
    -0.55
    POSITIVE LOGITS
     inherent
    1.06
     of
    1.02
    lessness
    1.01
     afforded
    0.98
     thereof
    0.93
    abl
    0.90
    fulness
    0.86
    iness
    0.81
    ality
    0.81
    lihood
    0.80
    Activations Density 0.208%

    No Known Activations