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. 15436
    Prev
    Next
    INDEX
    Explanations

    the verb "do" occurring in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating actions, decisions, or outcomes in various contexts

    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
     Coach
    -0.67
     Mages
    -0.63
     thous
    -0.59
     coach
    -0.58
    asso
    -0.56
    ascript
    -0.55
     charism
    -0.54
    puter
    -0.54
     Arena
    -0.53
     �
    -0.53
    POSITIVE LOGITS
    pload
    0.76
    iw
    0.75
    roads
    0.73
    ggles
    0.71
    conom
    0.70
    rake
    0.67
    rive
    0.66
    wolves
    0.66
    Sov
    0.66
    lim
    0.64
    Activations Density 0.348%

    No Known Activations