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. 4-RES-JB
    6. 9830
    Prev
    Next
    INDEX
    Explanations

    negative superlatives, specifically the word "least."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating minimal or low conditions

    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
    ses
    -0.73
    halla
    -0.72
    clerosis
    -0.70
    krit
    -0.68
    prototype
    -0.66
    bj
    -0.66
    selves
    -0.65
    kas
    -0.65
    bind
    -0.65
    raltar
    -0.64
    POSITIVE LOGITS
     imaginable
    0.79
     practicable
    0.78
     conceivable
    0.77
     toler
    0.76
     plausible
    0.75
     intrusive
    0.74
     amount
    0.71
     favourable
    0.70
     possible
    0.70
     conspicuous
    0.69
    Activations Density 0.016%

    No Known Activations