© 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. 8-RES-JB
    11. 4246
    Prev
    Next
    INDEX
    Explanations

    phrases related to receiving promotional offers and updates in junk mail or email communications

    oai_token-act-pair · gpt-3.5-turbo

    terms related to promotional offers and subscriptions

    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
    mand
    -0.64
    neapolis
    -0.60
    closed
    -0.60
    ibal
    -0.58
    liest
    -0.58
    Registered
    -0.57
    conn
    -0.56
    gone
    -0.56
    iter
    -0.56
     imped
    -0.55
    POSITIVE LOGITS
     occasional
    0.82
    ctory
    0.77
    poons
    0.74
    inkle
    0.64
    Content
    0.63
     .)
    0.63
    )=(
    0.62
    CRIP
    0.61
    pring
    0.61
    ãĥĩ
    0.61
    Activations Density 0.025%

    No Known Activations