© 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. 13793
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "double"

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to double standards in various contexts

    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
    utical
    -0.78
    uary
    -0.75
    omo
    -0.74
    onite
    -0.74
    ONY
    -0.73
    ALE
    -0.73
    istry
    -0.68
    orio
    -0.68
    edIn
    -0.68
    uria
    -0.68
    POSITIVE LOGITS
    header
    1.07
     sided
    0.98
     digit
    0.95
    headers
    0.95
     digits
    0.89
     dipping
    0.89
    plet
    0.86
     edged
    0.84
     Decker
    0.81
    think
    0.78
    Activations Density 0.030%

    No Known Activations