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. 4254
    Prev
    Next
    INDEX
    Explanations

    the word "obviously" within sentences

    oai_token-act-pair · gpt-3.5-turbo

    the word "obviously" and its variations to indicate certainty or emphasis

    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
    enced
    -0.78
    board
    -0.76
    mission
    -0.72
    nan
    -0.71
    arthed
    -0.71
    insula
    -0.70
    ENC
    -0.69
    uese
    -0.69
    lé
    -0.69
    bucks
    -0.67
    POSITIVE LOGITS
    NULL
    0.90
     identifiable
    0.71
    س
    0.70
     correct
    0.70
     parted
    0.66
     deline
    0.66
     inherit
    0.65
     inher
    0.64
     belonged
    0.64
     belongs
    0.63
    Activations Density 0.023%

    No Known Activations