Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 2586
    Prev
    Next
    INDEX
    Explanations

    formal written documents or communications, such as letters, memos, resolutions, statements, articles, and directives

    oai_token-act-pair · gpt-3.5-turbo

    official documents or communications such as letters, statements, and resolutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hindsight
    -0.61
    aughs
    -0.57
     Rebell
    -0.57
     accur
    -0.57
     spills
    -0.56
     newcomers
    -0.56
     memories
    -0.56
     Decay
    -0.54
    comes
    -0.54
     racks
    -0.53
    POSITIVE LOGITS
     outlining
    0.91
     stating
    0.87
     titled
    0.85
     whereby
    0.82
     indicating
    0.81
     wherein
    0.79
     thanking
    0.78
     exposing
    0.78
     recommending
    0.78
     alleging
    0.77
    Activations Density 0.304%

    No Known Activations