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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-RES-JB
    6. 8685
    Prev
    Next
    INDEX
    Explanations

    instances of contempt-related language or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "contempt" and its variations in the context of legal or social issues

    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
    eor
    -0.82
    mith
    -0.66
    ramid
    -0.65
    akeru
    -0.62
    jc
    -0.62
    laus
    -0.60
    ded
    -0.59
     sund
    -0.59
     Lans
    -0.58
    arist
    -0.57
    POSITIVE LOGITS
    uously
    1.45
    uous
    1.44
     contempt
    1.04
    naire
    0.98
    ible
    0.94
    uality
    0.86
    fully
    0.85
    ibly
    0.82
    antly
    0.81
    isons
    0.79
    Activations Density 0.010%

    No Known Activations