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. 22887
    Prev
    Next
    INDEX
    Explanations

    paragraph separators, such as "Ċ," in the text

    oai_token-act-pair · gpt-3.5-turbo

    web navigation elements, specifically links or calls to action

    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
     instinct
    -0.74
     ambassadors
    -0.69
     punish
    -0.68
     mas
    -0.68
     regenerate
    -0.64
     appar
    -0.64
    ensibly
    -0.63
     rotation
    -0.63
     reversing
    -0.63
     bending
    -0.63
    POSITIVE LOGITS
    ----------------------------------------------------------------
    0.91
    Tags
    0.87
    <|endoftext|>
    0.86
    Conclusion
    0.84
    SOURCE
    0.84
    --------------------------------------------------------
    0.82
    TAG
    0.81
    -+-+
    0.80
    ================================================================
    0.80
    Download
    0.79
    Activations Density 0.543%

    No Known Activations