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

    Neuronpedia

    Jacobian LensNEW
    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. 3263
    Prev
    Next
    INDEX
    Explanations

    phrases related to offering something for free or without charge

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to free offerings and subscription options

    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
    hap
    -0.76
    aukee
    -0.69
    RESULTS
    -0.64
     toughness
    -0.63
     scen
    -0.63
     evenly
    -0.63
     misfortune
    -0.62
     hardness
    -0.61
    igans
    -0.61
    lihood
    -0.60
    POSITIVE LOGITS
     subscription
    0.88
     subscriptions
    0.84
     ads
    0.80
     Payments
    0.75
     Ads
    0.75
    charge
    0.75
    Google
    0.71
     coupon
    0.71
     charge
    0.71
    Subscribe
    0.70
    Activations Density 0.053%

    No Known Activations