© 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. 0-RES-JB
    11. 13494
    Prev
    Next
    INDEX
    Explanations

    references to a specific location called "Santa Monica."

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Monica."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     injection
    -0.69
    rad
    -0.69
    sign
    -0.65
    OWER
    -0.65
    OLD
    -0.65
     unders
    -0.63
    ERG
    -0.63
     scouts
    -0.63
    OW
    -0.63
     eng
    -0.62
    POSITIVE LOGITS
     Monica
    3.84
     Paula
    2.11
     Anita
    1.76
     Clara
    1.46
     Teresa
    1.39
     Barbara
    1.37
     Ana
    1.35
     Rita
    1.35
     Huma
    1.34
     Elena
    1.33
    Activations Density 0.019%

    No Known Activations