© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 12516
    Prev
    Next
    INDEX
    Explanations

    phrases related to flipping, like "flip of the cards" or "flip a coin"

    oai_token-act-pair · gpt-3.5-turbo

    references to flipping or turning actions

    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
     uncond
    -0.78
    auna
    -0.77
    lain
    -0.73
    ļéĨĴ
    -0.67
    cliffe
    -0.66
    leground
    -0.65
    Private
    -0.62
    mobi
    -0.62
    CVE
    -0.59
     fullest
    -0.58
    POSITIVE LOGITS
     dice
    0.96
     punches
    0.81
     coin
    0.78
     Dice
    0.75
    Sax
    0.69
    wiki
    0.68
     scales
    0.68
     captcha
    0.66
     Screw
    0.65
     fingers
    0.64
    Activations Density 0.113%

    No Known Activations