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

    Neuronpedia

    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. 10-RES-JB
    11. 10663
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to family members

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and references to people, particularly the subject "he."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Govern
    -0.75
    idate
    -0.73
    cens
    -0.71
     Defendant
    -0.70
    lead
    -0.70
    ablishment
    -0.68
    akedown
    -0.66
    èĢħ
    -0.65
    Opp
    -0.64
     Defendants
    -0.64
    POSITIVE LOGITS
     remembers
    1.41
     awoke
    1.25
     regrets
    1.23
     admits
    1.18
     woke
    1.17
     reminis
    1.17
     recalls
    1.17
     graduated
    1.17
     joked
    1.15
     loves
    1.15
    Activations Density 0.364%

    No Known Activations