© 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. 23660
    Prev
    Next
    INDEX
    Explanations

    adverbs expressing likelihood or possibility

    oai_token-act-pair · gpt-3.5-turbo

    words expressing probability or likelihood

    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
    regate
    -0.92
    atur
    -0.86
    galitarian
    -0.79
    alg
    -0.76
    ibilities
    -0.73
    olls
    -0.73
    fy
    -0.73
    vae
    -0.73
    ifts
    -0.72
    idates
    -0.72
    POSITIVE LOGITS
     implying
    1.26
     indicating
    1.19
     preferring
    1.15
     culminating
    1.13
     comprising
    1.12
     excluding
    1.11
     consisting
    1.10
     involving
    1.10
     suggesting
    1.09
     relying
    1.09
    Activations Density 0.150%

    No Known Activations