© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11413
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the availability or current state of something, often in a promotional or informative context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "now" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    furt
    -0.74
    tnc
    -0.69
    andr
    -0.69
    zag
    -0.68
    gling
    -0.66
    speech
    -0.64
    benefit
    -0.64
    lav
    -0.62
    phen
    -0.62
    vation
    -0.62
    POSITIVE LOGITS
     Available
    1.28
     available
    1.15
     defunct
    1.14
    adays
    1.03
     discontinued
    0.96
    available
    0.95
     archived
    0.91
     officially
    0.91
     includes
    0.89
     deprecated
    0.89
    Activations Density 0.099%

    No Known Activations