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. 8-RES-JB
    6. 9739
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "which"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "which" and related phrases suggesting clarification or specification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seym
    -0.59
     Ott
    -0.58
     Brus
    -0.57
    bye
    -0.55
    Standing
    -0.55
     Patri
    -0.54
     Standing
    -0.54
     Bucc
    -0.54
    Bride
    -0.53
    Talk
    -0.53
    POSITIVE LOGITS
     comprises
    0.74
    zbollah
    0.71
    ;;;;;;;;;;;;
    0.71
     consists
    0.70
    nces
    0.68
    netflix
    0.67
    imes
    0.67
    embed
    0.66
     consisted
    0.66
    includes
    0.64
    Activations Density 0.070%

    No Known Activations