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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 22235
    Prev
    Next
    INDEX
    Explanations

    actions related to decision-making

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "choose to" indicating decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    til
    -0.77
     Canary
    -0.69
    listed
    -0.68
    ILY
    -0.68
     reperto
    -0.64
    inguished
    -0.62
    ritical
    -0.62
    pins
    -0.62
     manuscripts
    -0.61
     Five
    -0.61
    POSITIVE LOGITS
     pursue
    1.08
     ignore
    0.99
     make
    0.99
     explore
    0.97
     give
    0.97
     maximize
    0.96
     prioritize
    0.96
     minimize
    0.96
     create
    0.94
     marry
    0.94
    Activations Density 0.067%

    No Known Activations