© 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. 11-RES-JB
    11. 3484
    Prev
    Next
    INDEX
    Explanations

    texts related to policies, terms of service, and disclosures

    oai_token-act-pair · gpt-3.5-turbo

    references to legal and policy documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ranked
    -0.79
    wives
    -0.73
     counted
    -0.72
     improvised
    -0.68
     propelled
    -0.66
     catapult
    -0.66
     boosted
    -0.66
    icted
    -0.65
     slain
    -0.64
     starved
    -0.63
    POSITIVE LOGITS
     Terms
    1.44
     disclaimer
    1.36
     Agreement
    1.36
     Policies
    1.33
     Privacy
    1.32
     FAQ
    1.26
     Conditions
    1.24
     disclaim
    1.24
     Compliance
    1.23
    Privacy
    1.15
    Activations Density 0.231%

    No Known Activations