© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 7455
    Prev
    Next
    INDEX
    Explanations

    phrases related to newsletters and daily updates

    oai_token-act-pair · gpt-3.5-turbo

    mentions of daily newsletters and subscriptions

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

    No Comments

    Negative Logits
    RIP
    -0.82
    ional
    -0.77
     JPM
    -0.75
    yo
    -0.71
    arov
    -0.71
    imo
    -0.69
    witz
    -0.68
    abal
    -0.68
     Hicks
    -0.66
    quartered
    -0.65
    POSITIVE LOGITS
     subscription
    0.80
     traveller
    0.76
     Travels
    0.73
    ottest
    0.71
     certs
    0.71
     premium
    0.69
     Container
    0.68
     foothold
    0.66
     newsletter
    0.66
     roundup
    0.66
    Activations Density 0.043%

    No Known Activations