© 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. 2-RES-JB
    11. 9177
    Prev
    Next
    INDEX
    Explanations

    the word "Mom" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to "Mom" 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
     commission
    -0.75
     reserved
    -0.73
     date
    -0.71
     challenge
    -0.71
    chnology
    -0.69
    punk
    -0.68
    ngth
    -0.67
    Ĥ¬
    -0.67
     balance
    -0.67
    interstitial
    -0.66
    POSITIVE LOGITS
    Mom
    1.09
    Dad
    1.01
     Dug
    0.99
    nel
    0.95
     Dad
    0.92
    my
    0.92
    mers
    0.90
     Mom
    0.85
    zilla
    0.85
    ents
    0.83
    Activations Density 0.009%

    No Known Activations