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. 18977
    Prev
    Next
    INDEX
    Explanations

    the adjective "sheer" followed by a word denoting quantity or intensity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sheer" and related concepts indicating a sense of vastness or intensity

    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
    anwhile
    -0.93
    afort
    -0.81
    iotics
    -0.76
    artments
    -0.76
    azel
    -0.74
    doctor
    -0.73
    ublic
    -0.72
    lict
    -0.71
    azine
    -0.70
    bye
    -0.69
    POSITIVE LOGITS
     coincidence
    0.95
     volume
    0.93
     quantity
    0.88
    tons
    0.85
     numbers
    0.84
     sheer
    0.81
     quantities
    0.78
     unbeliev
    0.76
     numerical
    0.76
    ãĤ¨ãĥ«
    0.74
    Activations Density 0.012%

    No Known Activations