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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 8513
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to finding common ground or shared agreements

    oai_token-act-pair · gpt-3.5-turbo

    references to common ground or consensus in discussions

    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
     notor
    -0.71
    atto
    -0.69
     tatt
    -0.68
     bil
    -0.66
    glomer
    -0.63
    uked
    -0.61
     bailed
    -0.60
     accomp
    -0.60
    hid
    -0.60
    pload
    -0.59
    POSITIVE LOGITS
     footing
    0.76
    places
    0.76
    cover
    0.73
    notes
    0.71
    aminer
    0.69
    ¢
    0.66
    Ground
    0.66
    enture
    0.65
    planes
    0.65
    itement
    0.64
    Activations Density 0.014%

    No Known Activations