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. 2-RES-JB
    6. 8668
    Prev
    Next
    INDEX
    Explanations

    words related to acceptance or agreement

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "accommodation."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VID
    -0.87
    vous
    -0.86
    prototype
    -0.82
    geist
    -0.76
     Dare
    -0.74
     hope
    -0.73
    OPLE
    -0.73
    çīĪ
    -0.70
    trap
    -0.68
    hs
    -0.67
    POSITIVE LOGITS
    reditation
    1.10
    redited
    1.04
    enture
    1.02
     acc
    0.97
    ursed
    0.93
    atech
    0.91
    imate
    0.91
    licted
    0.90
    retion
    0.90
    ommod
    0.89
    Activations Density 0.005%

    No Known Activations