© 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. 7-RES-JB
    11. 22955
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and possessive pronouns with a focus on past actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and references to people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Globe
    -0.75
     Aden
    -0.70
     Welch
    -0.68
    elsen
    -0.68
     Akron
    -0.67
     Sund
    -0.67
     Kinn
    -0.67
     Dome
    -0.66
     Kush
    -0.66
     Vers
    -0.63
    POSITIVE LOGITS
    'll
    1.14
    'd
    1.12
    're
    1.06
    've
    1.03
     could
    0.95
    'm
    0.86
     shouldn
    0.84
     intend
    0.84
     couldn
    0.84
     wouldn
    0.82
    Activations Density 0.216%

    No Known Activations