© 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. 17505
    Prev
    Next
    INDEX
    Explanations

    hyphenated words with negative connotations

    oai_token-act-pair · gpt-3.5-turbo

    references to high-profile events or individuals

    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
    ulhu
    -0.91
     Dickinson
    -0.79
     Cassidy
    -0.78
    ħĭ
    -0.75
     Rica
    -0.74
    ļéĨĴ
    -0.72
     AVG
    -0.71
     EntityItem
    -0.70
    HCR
    -0.70
     Vessel
    -0.67
    POSITIVE LOGITS
    sized
    1.27
    level
    1.14
    based
    1.08
    issue
    1.07
    function
    1.05
    powered
    1.05
    eyed
    1.03
    distance
    1.03
    exclusive
    1.00
    trial
    0.98
    Activations Density 0.398%

    No Known Activations