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. 8-RES-JB
    6. 5338
    Prev
    Next
    INDEX
    Explanations

    religious or spiritual references and phrases

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and sentence endings

    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
     quir
    -1.01
     billed
    -0.81
     tack
    -0.79
     volunte
    -0.78
     babys
    -0.78
    ewater
    -0.77
     batted
    -0.77
     billing
    -0.77
     booking
    -0.77
     staging
    -0.77
    POSITIVE LOGITS
     Hence
    1.71
     Thus
    1.68
     Therefore
    1.63
     Accordingly
    1.57
     Moreover
    1.49
     Consequently
    1.46
     Such
    1.43
     Likewise
    1.34
    Thus
    1.32
     Nevertheless
    1.31
    Activations Density 0.339%

    No Known Activations