© 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. 10-RES-JB
    11. 16569
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations, particularly New England

    oai_token-act-pair · gpt-3.5-turbo

    mentions of New England and related locations

    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
    letters
    -0.80
    relation
    -0.79
    ãĤ¼ãĤ¦ãĤ¹
    -0.79
    zona
    -0.76
    ynt
    -0.76
    byn
    -0.74
    =-=-=-=-=-=-=-=-
    -0.72
    Bir
    -0.64
    workshop
    -0.64
    odan
    -0.63
    POSITIVE LOGITS
     Patriots
    1.00
    ers
    0.82
     Pelicans
    0.78
     Athletic
    0.76
     Edison
    0.75
     Correctional
    0.75
     Railroad
    0.71
    phrine
    0.69
     State
    0.68
     Governors
    0.68
    Activations Density 0.066%

    No Known Activations