© 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. 3071
    Prev
    Next
    INDEX
    Explanations

    specific phrases encouraging newsletter subscriptions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the source of information or stories

    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
    imates
    -0.77
    imental
    -0.75
    heim
    -0.74
    imate
    -0.73
    omsky
    -0.69
    gow
    -0.69
    Í
    -0.67
     retard
    -0.65
    RGB
    -0.62
    hetics
    -0.62
    POSITIVE LOGITS
     clicking
    1.35
     signing
    1.18
     subscribing
    1.16
     bookmark
    1.08
     downloading
    1.06
     submitting
    1.03
     joining
    1.01
     selecting
    1.01
     liking
    0.98
     visiting
    0.96
    Activations Density 0.026%

    No Known Activations