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. 8-RES-JB
    6. 22139
    Prev
    Next
    INDEX
    Explanations

    proper nouns such as names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "said" and related expressions of speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à¦
    -0.68
    Cop
    -0.68
     ILCS
    -0.66
    aspx
    -0.66
     Judicial
    -0.65
    SPONSORED
    -0.64
    Justice
    -0.63
    Pont
    -0.63
    Anti
    -0.60
     lyn
    -0.59
    POSITIVE LOGITS
     goodbye
    1.19
     farewell
    0.94
     afterwards
    0.90
     hello
    0.90
     aloud
    0.89
     afterward
    0.88
     bluntly
    0.85
     beforehand
    0.82
     confidently
    0.82
     proudly
    0.81
    Activations Density 0.273%

    No Known Activations