© 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. 4-RES-JB
    11. 24332
    Prev
    Next
    INDEX
    Explanations

    instances of the word "mold", with a higher activation for the specific word "mold" compared to variations like "mould" or "molded"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of mold and related terms

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

    No Comments

    Negative Logits
    avez
    -0.69
    IGHTS
    -0.67
    vernment
    -0.66
     derog
    -0.66
    tein
    -0.66
    abeth
    -0.65
    externalActionCode
    -0.64
    pri
    -0.64
     WTO
    -0.62
    OUP
    -0.62
    POSITIVE LOGITS
     mold
    1.09
     mould
    1.06
    ering
    0.99
     molded
    0.86
    eus
    0.84
     spores
    0.82
    ovan
    0.82
    ings
    0.81
    eers
    0.80
    erer
    0.80
    Activations Density 0.011%

    No Known Activations