© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 23361
    Prev
    Next
    INDEX
    Explanations

    phrases related to user actions on a website, specifically selecting a newsletter to subscribe to

    oai_token-act-pair · gpt-3.5-turbo

    mandatory requirements or actions that need to be taken

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    banks
    -0.63
     implying
    -0.61
     portraying
    -0.58
     justifying
    -0.56
     influencing
    -0.55
    uman
    -0.55
     advocating
    -0.55
    bent
    -0.55
    gettable
    -0.55
    forced
    -0.54
    POSITIVE LOGITS
     reload
    0.76
     login
    0.75
     Javascript
    0.75
     Submit
    0.70
    ionic
    0.66
     contact
    0.65
    submit
    0.63
    register
    0.63
    arate
    0.63
     submit
    0.62
    Activations Density 0.023%

    No Known Activations