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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4736
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters

    oai_token-act-pair · gpt-3.5-turbo

    reference to the state or status of individuals or entities

    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
    inventoryQuantity
    -0.79
    estyles
    -0.75
    itiveness
    -0.72
    ieties
    -0.70
    ptoms
    -0.69
     heights
    -0.69
    isons
    -0.68
    natureconservancy
    -0.68
     grit
    -0.68
     deform
    -0.68
    POSITIVE LOGITS
     obligated
    1.18
     employed
    1.09
     unaware
    1.05
     affiliated
    1.04
     authorized
    1.03
     aware
    1.02
     responsible
    1.01
     authorised
    1.00
     ineligible
    1.00
     representing
    0.97
    Activations Density 0.247%

    No Known Activations