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. 1121
    Prev
    Next
    INDEX
    Explanations

    words related to actions or objects involving biting or gnawing

    oai_token-act-pair · gpt-3.5-turbo

    words related to food, particularly snacks or small bites

    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
     Wink
    -0.76
     Princ
    -0.76
    tes
    -0.76
     Goth
    -0.71
    GBT
    -0.70
    fitting
    -0.69
    YL
    -0.68
    asar
    -0.68
     Painter
    -0.67
     Malk
    -0.66
    POSITIVE LOGITS
    hig
    0.88
     gn
    0.83
     hors
    0.79
     nib
    0.78
    meat
    0.77
     nood
    0.76
     scratch
    0.75
     pri
    0.75
    agues
    0.75
     spoon
    0.73
    Activations Density 0.014%

    No Known Activations