© 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. 3-RES-JB
    11. 16238
    Prev
    Next
    INDEX
    Explanations

    phrases indicating frequency or repetition

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "often."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imming
    -0.78
    ENE
    -0.72
    =]
    -0.72
    ilts
    -0.70
    RAW
    -0.70
    andan
    -0.69
    Wi
    -0.69
    SG
    -0.68
    kind
    -0.68
     Melt
    -0.67
    POSITIVE LOGITS
    entimes
    1.11
     encountered
    0.89
    interstitial
    0.87
    theless
    0.84
     resorted
    0.82
    è¦ļéĨĴ
    0.82
     relied
    0.81
     overlooked
    0.81
     times
    0.80
     Asked
    0.79
    Activations Density 0.034%

    No Known Activations