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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 4124
    Prev
    Next
    INDEX
    Explanations

    personal information related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms that indicate ownership or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pty
    -0.83
    yrs
    -0.79
     Canaver
    -0.76
    chers
    -0.76
    mir
    -0.76
    quished
    -0.75
    icably
    -0.72
    ij士
    -0.70
    agles
    -0.70
    TAIN
    -0.69
    POSITIVE LOGITS
     own
    1.42
     surroundings
    1.20
     identity
    1.08
     genitals
    1.06
     behavior
    1.03
     preferences
    1.03
     favourite
    1.02
     personality
    1.01
     favorite
    1.01
     behaviour
    1.01
    Activations Density 0.275%

    No Known Activations