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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 5348
    Prev
    Next
    INDEX
    Explanations

    action verbs related to cooking and preparing food dishes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "stir" and its variations in various contexts

    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
    iary
    -0.91
    ocado
    -0.77
     Mavericks
    -0.70
    iaries
    -0.68
    ecause
    -0.67
    omial
    -0.66
     Grizzlies
    -0.62
    ouf
    -0.62
    jamin
    -0.62
    istance
    -0.62
    POSITIVE LOGITS
    rings
    0.98
     stir
    0.96
     stirring
    0.90
    rer
    0.90
     stirred
    0.89
    rers
    0.87
    lings
    0.83
     fry
    0.82
    rament
    0.76
    mong
    0.75
    Activations Density 0.020%

    No Known Activations