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. 8-RES-JB
    6. 4442
    Prev
    Next
    INDEX
    Explanations

    references to daily newsletters

    oai_token-act-pair · gpt-3.5-turbo

    mentions of daily newsletters and similar subscription terms

    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
    essee
    -0.83
    schild
    -0.78
    kj
    -0.76
    abase
    -0.75
    alus
    -0.70
    olina
    -0.68
    alez
    -0.68
    quartered
    -0.67
    rehens
    -0.66
     Gould
    -0.66
    POSITIVE LOGITS
     dose
    0.89
     newsletter
    0.80
     roundup
    0.77
     updates
    0.74
     reminder
    0.73
     update
    0.70
     glimpse
    0.67
     newsletters
    0.66
     recap
    0.64
     Travels
    0.63
    Activations Density 0.017%

    No Known Activations