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. 9-RES-JB
    6. 558
    Prev
    Next
    INDEX
    Explanations

    instances of the word "before"

    oai_token-act-pair · gpt-3.5-turbo

    references to prior occurrences or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erville
    -0.62
     equivalent
    -0.59
    atana
    -0.58
     cones
    -0.56
    urther
    -0.55
    ãĥ¼ãĥ
    -0.54
    utenberg
    -0.53
    arov
    -0.52
    equal
    -0.52
    BAT
    -0.52
    POSITIVE LOGITS
    .
    0.74
    ;
    0.73
     committing
    0.70
     settling
    0.69
    ebin
    0.67
    isner
    0.66
    mort
    0.66
    hand
    0.65
     donating
    0.64
     realizing
    0.62
    Activations Density 0.077%

    No Known Activations