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. 14177
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically the name "Holland."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Holland."

    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
    culation
    -0.87
    ctic
    -0.80
    ramid
    -0.77
    ãĥ£
    -0.76
    ceed
    -0.76
    vae
    -0.76
    ccording
    -0.74
    itutes
    -0.74
    ormal
    -0.73
    notations
    -0.73
    POSITIVE LOGITS
     Holland
    0.98
    inson
    0.91
    shire
    0.90
    stadt
    0.84
     Gardens
    0.79
     Gaal
    0.76
     Cob
    0.75
    ijn
    0.74
     Tunnel
    0.73
     Wink
    0.73
    Activations Density 0.010%

    No Known Activations