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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 5507
    Prev
    Next
    INDEX
    Explanations

    verbs related to loud vocal expressions or outcries

    oai_token-act-pair · gpt-3.5-turbo

    instances of vocal expressions of urgency or emotion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    folios
    -0.82
    folio
    -0.78
    algia
    -0.77
    uncture
    -0.75
    flix
    -0.70
    amation
    -0.70
    å§«
    -0.67
     Democr
    -0.66
    nesota
    -0.66
    ãĥ´
    -0.66
    POSITIVE LOGITS
     louder
    1.12
     loudly
    0.99
     aloud
    0.86
     shout
    0.85
     slogans
    0.83
     goodbye
    0.83
     shouted
    0.81
     yells
    0.80
     shouting
    0.80
     yelling
    0.79
    Activations Density 0.030%

    No Known Activations