© 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. 9-RES-JB
    11. 15949
    Prev
    Next
    INDEX
    Explanations

    words related to eligibility or qualifications

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" and its various forms indicating eligibility or permission

    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
     reminding
    -0.75
     seeming
    -0.70
     forgetting
    -0.70
    quickShipAvailable
    -0.65
     soothing
    -0.65
    getting
    -0.64
    going
    -0.64
     distractions
    -0.64
     crumbling
    -0.63
     calming
    -0.63
    POSITIVE LOGITS
     participate
    1.50
     qualify
    1.33
     receive
    1.28
     enter
    1.24
     operate
    1.23
     perform
    1.17
     apply
    1.12
     partake
    1.11
     administer
    1.10
     attend
    1.10
    Activations Density 0.288%

    No Known Activations