© 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 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. 2-RES-JB
    11. 7553
    Prev
    Next
    INDEX
    Explanations

    instances of the word "suppress" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to suppression or control

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sen
    -0.73
    Äį
    -0.71
    debian
    -0.71
    docker
    -0.70
    rians
    -0.70
    owitz
    -0.69
    deals
    -0.68
    WHERE
    -0.68
    Sky
    -0.68
    sky
    -0.67
    POSITIVE LOGITS
     suppress
    1.09
     suppression
    1.02
     suppressing
    0.99
    ively
    0.97
     suppressed
    0.96
     muzzle
    0.82
    ences
    0.71
     inhib
    0.68
    uous
    0.68
     cooker
    0.68
    Activations Density 0.015%

    No Known Activations