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. 19475
    Prev
    Next
    INDEX
    Explanations

    verbs that imply a call to action or a need for change

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs and auxiliary verbs indicating obligation or capability

    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
    bury
    -0.57
    hin
    -0.55
    hack
    -0.54
     KL
    -0.53
    inkle
    -0.52
     latter
    -0.52
     afore
    -0.51
    ciation
    -0.51
    omial
    -0.50
    UFF
    -0.50
    POSITIVE LOGITS
     hereby
    0.66
     virtually
    0.62
     unmist
    0.62
     nevertheless
    0.62
    NetMessage
    0.61
     compelled
    0.60
    ãĥĦ
    0.60
     nonetheless
    0.59
    pmwiki
    0.59
    ãĥĩãĤ£
    0.58
    Activations Density 0.717%

    No Known Activations