© 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. 19815
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "dumb" used in a negative context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dumb" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    OHN
    -0.77
    AUT
    -0.75
    apers
    -0.69
    akings
    -0.68
    ________________________________________________________________
    -0.68
    APH
    -0.66
    Downloadha
    -0.66
    EB
    -0.65
    20439
    -0.64
    aunder
    -0.64
    POSITIVE LOGITS
     dumb
    1.03
    founded
    0.96
    found
    0.94
    bell
    0.87
     Dumb
    0.87
    wallet
    0.85
    gest
    0.84
    stru
    0.82
    ness
    0.79
    mund
    0.78
    Activations Density 0.004%

    No Known Activations