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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19597
    Prev
    Next
    INDEX
    Explanations

    sentences that end abruptly with punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    statements or sentences that conclude or summarize information

    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
     inward
    -0.76
     inco
    -0.75
     sovereignty
    -0.74
    antz
    -0.74
     unrest
    -0.73
     inciting
    -0.72
     overt
    -0.71
    ism
    -0.71
     antit
    -0.71
     disson
    -0.71
    POSITIVE LOGITS
     Alternatively
    1.36
     Depending
    1.32
     Simply
    1.23
     Luckily
    1.16
     However
    1.16
     Otherwise
    1.14
     Besides
    1.13
     Thankfully
    1.12
     Especially
    1.10
     Unfortunately
    1.10
    Activations Density 0.537%

    No Known Activations