© 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. 10-RES-JB
    11. 2295
    Prev
    Next
    INDEX
    Explanations

    requests to sign up for a newsletter

    oai_token-act-pair · gpt-3.5-turbo

    instances of calls to action related to signing up for a newsletter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.83
    schild
    -0.81
    »Ĵ
    -0.72
    ĸļ
    -0.72
    rency
    -0.70
     heel
    -0.70
     aven
    -0.65
     rook
    -0.65
    amo
    -0.63
    oult
    -0.63
    POSITIVE LOGITS
     Thumbnails
    0.87
     Up
    0.75
    atures
    0.72
    azines
    0.71
     Picks
    0.69
     Messages
    0.68
    Increases
    0.68
     Newsletter
    0.67
     Subscribe
    0.64
    Send
    0.64
    Activations Density 0.020%

    No Known Activations