© 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. 2-RES-JB
    11. 17174
    Prev
    Next
    INDEX
    Explanations

    phrases related to subscribing to newsletters

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to subscribing to newsletters or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ball
    -0.88
    san
    -0.75
    pel
    -0.74
    pell
    -0.71
    talk
    -0.70
    bra
    -0.69
    footed
    -0.67
     rounding
    -0.67
    lake
    -0.67
     Morg
    -0.66
    POSITIVE LOGITS
     subscribing
    1.10
     subscriptions
    1.01
     subscribe
    0.94
    interstitial
    0.90
    ividual
    0.86
     subscription
    0.85
     subscribers
    0.82
     habits
    0.82
    iments
    0.82
     citiz
    0.80
    Activations Density 0.008%

    No Known Activations