© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 8267
    Prev
    Next
    INDEX
    Explanations

    pronouns and possessive pronouns referring to people

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and their references

    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
    —-
    -0.68
     Barrett
    -0.66
     Byr
    -0.65
    âĶĢ
    -0.63
     Layer
    -0.62
     Fleming
    -0.61
     Berman
    -0.58
     ÂŃ
    -0.58
     Edison
    -0.57
     Allied
    -0.56
    POSITIVE LOGITS
     favourite
    0.90
    anmar
    0.85
     favorite
    0.85
     own
    0.82
    panic
    0.81
    ullivan
    0.78
     Favorite
    0.77
    voice
    0.74
    Favorite
    0.74
    selves
    0.71
    Activations Density 0.072%

    No Known Activations