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. 10-RES-JB
    6. 1845
    Prev
    Next
    INDEX
    Explanations

    phrases related to consequences or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causation or the result of an action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pages
    -0.82
    andon
    -0.66
    mods
    -0.64
    itiveness
    -0.64
    views
    -0.64
    existent
    -0.64
    events
    -0.64
    files
    -0.64
    bu
    -0.63
    sama
    -0.62
    POSITIVE LOGITS
     result
    1.77
     consequence
    1.55
     precaution
    1.46
     prerequisite
    1.07
     reminder
    1.05
     testament
    1.05
     consolation
    0.99
     workaround
    0.97
     safeguard
    0.97
     matter
    0.97
    Activations Density 0.088%

    No Known Activations