© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 14919
    Prev
    Next
    INDEX
    Explanations

    words related to departure or leaving

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "out" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tyr
    -0.65
     etched
    -0.62
     indictment
    -0.60
     Brach
    -0.59
     Tsarnaev
    -0.59
     Mub
    -0.59
     Akin
    -0.58
     Coin
    -0.57
     Dude
    -0.57
     Publishers
    -0.56
    POSITIVE LOGITS
    lying
    1.44
    stretched
    1.38
    growth
    1.35
    lier
    1.30
    crop
    1.29
    posts
    1.27
    cro
    1.24
    flow
    1.24
    fitting
    1.23
    bur
    1.23
    Activations Density 0.031%

    No Known Activations