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. 6-RES-JB
    6. 6434
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating strong contrast

    oai_token-act-pair · gpt-3.5-turbo

    the word "stark" in various contexts, often relating to contrasts or notable differences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diligently
    -0.69
    ipop
    -0.69
     safely
    -0.68
    «ĺ
    -0.67
    APS
    -0.66
    hops
    -0.66
    annis
    -0.66
    uthor
    -0.65
    conservancy
    -0.65
    llular
    -0.64
    POSITIVE LOGITS
    ly
    1.16
     contrasts
    1.16
     contrast
    1.04
     stark
    0.92
    est
    0.89
    ness
    0.84
    er
    0.81
     difference
    0.79
    iary
    0.78
     naked
    0.78
    Activations Density 0.019%

    No Known Activations