© 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. 3191
    Prev
    Next
    INDEX
    Explanations

    verbs related to investigating or examining

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verbs "look" and "looking"

    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
    âĹ¼
    -0.67
    theless
    -0.65
    Ranked
    -0.64
    panic
    -0.64
     understatement
    -0.60
    Own
    -0.59
     Osw
    -0.59
     hugs
    -0.59
    âĢ¢âĢ¢
    -0.59
    CENT
    -0.57
    POSITIVE LOGITS
     into
    0.91
     suspic
    0.78
     forward
    0.77
     INTO
    0.76
    izons
    0.74
     unsuccessfully
    0.74
     closely
    0.73
     diligently
    0.68
    ression
    0.67
    oward
    0.66
    Activations Density 0.050%

    No Known Activations