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. 3-RES-JB
    6. 19761
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific name 'Wilbur'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "bur" within words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uncture
    -0.83
     SYSTEM
    -0.74
     partName
    -0.70
     Spac
    -0.69
     Dangerous
    -0.68
     Controlled
    -0.67
    perture
    -0.66
     Tune
    -0.62
     Scand
    -0.61
     Logged
    -0.60
    POSITIVE LOGITS
    querque
    1.25
    ger
    1.12
    idays
    1.01
    rowing
    0.98
    ging
    0.94
    rito
    0.94
    rows
    0.93
    geoning
    0.92
    sts
    0.91
    thur
    0.90
    Activations Density 0.006%

    No Known Activations