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. 9-RES-JB
    6. 20352
    Prev
    Next
    INDEX
    Explanations

    phrases related to superlatives or extreme qualities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating superlatives or notable qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥīãĥ©
    -0.77
    iances
    -0.72
    å§
    -0.72
    oros
    -0.71
    ume
    -0.70
    ãģĤ
    -0.69
    ãģ¦
    -0.68
    3333
    -0.66
    ibility
    -0.66
    WB
    -0.65
    POSITIVE LOGITS
     toughest
    1.43
     coolest
    1.42
     hardest
    1.38
     simplest
    1.35
     greatest
    1.33
     strongest
    1.32
     biggest
    1.30
     strang
    1.28
     smartest
    1.25
     weakest
    1.24
    Activations Density 0.130%

    No Known Activations