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. 1-RES-JB
    6. 17890
    Prev
    Next
    INDEX
    Explanations

    the word "Nice"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Nice" and its variations, indicating a positive sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WIND
    -0.85
    Ultra
    -0.77
    aer
    -0.75
    SUP
    -0.71
    produced
    -0.69
    OTT
    -0.69
    à¨
    -0.67
    interrupted
    -0.67
    à©
    -0.66
    ARY
    -0.66
    POSITIVE LOGITS
     Nice
    1.04
    nice
    1.01
    Nice
    0.99
     Guys
    0.84
     Guy
    0.84
     Pictures
    0.78
    cker
    0.73
    ï
    0.73
    hua
    0.72
    ctions
    0.71
    Activations Density 0.007%

    No Known Activations