© 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 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. 20674
    Prev
    Next
    INDEX
    Explanations

    references to a specific person indicated by the pronoun "him."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual

    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
    anking
    -0.63
    services
    -0.63
     Result
    -0.61
     Amanda
    -0.61
    itures
    -0.60
    reach
    -0.60
    give
    -0.60
    profits
    -0.59
     Annie
    -0.59
    mble
    -0.59
    POSITIVE LOGITS
     personally
    0.94
    panic
    0.88
     Majesty
    0.86
    ading
    0.85
    atically
    0.83
    atic
    0.82
    soever
    0.79
     orally
    0.77
    alian
    0.75
    zbollah
    0.73
    Activations Density 0.096%

    No Known Activations