© 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. 2-RES-JB
    11. 22582
    Prev
    Next
    INDEX
    Explanations

    references to the specific location of "Boca Raton"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location or entity, particularly "Boca Raton."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    schild
    -0.80
    culosis
    -0.79
    boxes
    -0.73
    cases
    -0.72
    dit
    -0.69
    ROR
    -0.68
    sg
    -0.66
    MENTS
    -0.64
    lights
    -0.63
    nir
    -0.63
    POSITIVE LOGITS
    oca
    1.34
     starch
    0.95
    uthor
    0.89
    issance
    0.84
    Cola
    0.81
    ignt
    0.79
     Lumpur
    0.79
    zyme
    0.77
    iliate
    0.76
    amera
    0.75
    Activations Density 0.008%

    No Known Activations