© 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. 11200
    Prev
    Next
    INDEX
    Explanations

    prompts related to subscribing or not subscribing to newsletters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to privacy and notice policies

    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
    uana
    -0.65
     coord
    -0.64
     patriarch
    -0.56
    pires
    -0.56
     simul
    -0.54
     scapego
    -0.53
     mun
    -0.53
     sugg
    -0.53
    Js
    -0.52
     retri
    -0.52
    POSITIVE LOGITS
    Privacy
    0.70
     Email
    0.68
     Submit
    0.65
     Newsletter
    0.64
     disclaimer
    0.60
    ļéĨĴ
    0.56
    Email
    0.56
    phrase
    0.55
     Divinity
    0.55
    antha
    0.54
    Activations Density 0.013%

    No Known Activations