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. 23115
    Prev
    Next
    INDEX
    Explanations

    action verbs in the past tense

    oai_token-act-pair · gpt-3.5-turbo

    action verbs related to physical processes or transformations

    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
    hov
    -0.77
    isode
    -0.67
    itar
    -0.65
    Nap
    -0.65
    istries
    -0.64
    hun
    -0.64
    arist
    -0.63
    church
    -0.63
    itarian
    -0.63
    cum
    -0.62
    POSITIVE LOGITS
    ynamic
    0.80
     separately
    0.77
     by
    0.75
     BY
    0.73
     externally
    0.72
     aback
    0.71
     Alive
    0.70
     horizontally
    0.70
     electronically
    0.69
    nesday
    0.68
    Activations Density 0.279%

    No Known Activations