Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23412
    Prev
    Next
    INDEX
    Explanations

    technology-related terms and choices in decision-making

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a decision-making process or choice

    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
    stood
    -0.60
     scrut
    -0.54
    ivering
    -0.53
    ibilities
    -0.52
    everal
    -0.52
     resurg
    -0.52
    collect
    -0.51
    pires
    -0.49
     milestones
    -0.49
    ankind
    -0.49
    POSITIVE LOGITS
     instead
    1.89
    instead
    1.62
     rather
    1.56
    Instead
    1.39
     Instead
    1.38
    rather
    1.34
     because
    1.08
     anyway
    1.05
     anyways
    1.05
     lest
    1.02
    Activations Density 0.796%

    No Known Activations