Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 20096
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of modesty or smallness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to income and economic modesty or budget limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    generic
    -0.80
    rael
    -0.69
     passionately
    -0.68
    wrong
    -0.68
    hops
    -0.65
    iph
    -0.65
    antis
    -0.64
    CI
    -0.63
     desperately
    -0.62
    iqueness
    -0.61
    POSITIVE LOGITS
     amounts
    1.29
     sized
    1.25
     amount
    1.22
    ly
    1.19
     quantities
    1.03
     sums
    1.02
     doses
    0.91
    mble
    0.89
     sum
    0.89
     compensation
    0.87
    Activations Density 0.132%

    No Known Activations