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. 6-RES-JB
    6. 23261
    Prev
    Next
    INDEX
    Explanations

    phrases comparing actions or choices between two alternatives, highlighting a preference for one over the other

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases emphasizing preference or choice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isf
    -0.73
    Aren
    -0.70
    iola
    -0.68
    MG
    -0.68
    Origin
    -0.67
    Corn
    -0.65
    lied
    -0.64
    ENE
    -0.64
    Accessory
    -0.64
    eneg
    -0.64
    POSITIVE LOGITS
     necessarily
    1.11
     relying
    0.94
     bothering
    0.90
     anything
    0.86
     outright
    0.86
     simply
    0.84
     merely
    0.84
     letting
    0.81
     bother
    0.78
     allowing
    0.77
    Activations Density 0.046%

    No Known Activations