© 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. 17307
    Prev
    Next
    INDEX
    Explanations

    terms related to legal rights and constitutional matters

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to civil rights and legal entitlements

    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
     magnification
    -0.78
     pans
    -0.75
     blitz
    -0.74
     gimm
    -0.73
     flashy
    -0.70
     Flare
    -0.70
     spoof
    -0.68
     Styles
    -0.68
     Chemistry
    -0.68
     tricks
    -0.67
    POSITIVE LOGITS
     entitled
    1.29
     lawfully
    1.23
     irrespective
    1.15
     entit
    1.12
     governed
    1.10
     endowed
    1.07
     oppressed
    1.04
    subject
    1.03
     deserving
    1.01
     obligated
    1.01
    Activations Density 0.393%

    No Known Activations