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. 4-RES-JB
    6. 8199
    Prev
    Next
    INDEX
    Explanations

    verbs related to making decisions

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "decided"

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

    No Comments

    Negative Logits
    ikan
    -0.74
    abytes
    -0.67
    ciating
    -0.66
    isha
    -0.66
    igi
    -0.66
    esc
    -0.65
    izont
    -0.65
    gae
    -0.65
    clad
    -0.64
    ithing
    -0.64
    POSITIVE LOGITS
     Garc
    0.81
     unanimously
    0.75
     decided
    0.75
     decides
    0.74
    ters
    0.69
     decide
    0.69
     upon
    0.68
     chose
    0.67
     chooses
    0.62
     anew
    0.62
    Activations Density 0.031%

    No Known Activations