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. 11-RES-JB
    6. 19406
    Prev
    Next
    INDEX
    Explanations

    phrases related to events, actions, and consequences

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant negative consequences or warnings related to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Their
    -1.31
    their
    -1.31
     Their
    -1.16
     THEIR
    -1.05
    They
    -1.05
    they
    -0.97
     They
    -0.90
     theirs
    -0.87
    his
    -0.87
    His
    -0.87
    POSITIVE LOGITS
     organizers
    0.93
     participants
    0.92
     proponents
    0.91
     lawmakers
    0.90
     analysts
    0.86
     critics
    0.86
     contestants
    0.85
     officials
    0.85
     organisers
    0.85
     opponents
    0.84
    Activations Density 1.018%

    No Known Activations