© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 6733
    Prev
    Next
    INDEX
    Explanations

    comparatives and superlatives related to size

    oai_token-act-pair · gpt-3.5-turbo

    the word "larger" and its various contexts related to size or magnitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lly
    -0.71
    jad
    -0.65
    jo
    -0.64
    ?,
    -0.62
    aria
    -0.62
    bia
    -0.61
    tha
    -0.61
    mone
    -0.60
    urn
    -0.59
    iev
    -0.59
    POSITIVE LOGITS
     larger
    3.40
     bigger
    2.69
     smaller
    2.48
     wider
    2.26
     broader
    2.02
    larg
    1.96
     narrower
    1.91
     greater
    1.84
     taller
    1.84
     large
    1.81
    Activations Density 0.011%

    No Known Activations