© 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. 20862
    Prev
    Next
    INDEX
    Explanations

    locations or entities related to the word 'Penn'

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Penn" or variations thereof

    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
    eer
    -0.79
     cerebral
    -0.67
     willful
    -0.64
    eering
    -0.63
    PRES
    -0.62
     Alz
    -0.60
    semble
    -0.59
     rall
    -0.59
     Norn
    -0.59
    TextColor
    -0.58
    POSITIVE LOGITS
    sylv
    1.50
    sylvania
    1.39
    iless
    1.18
    insula
    1.09
    sat
    0.99
    olini
    0.96
    essee
    0.92
    sburg
    0.91
    itude
    0.89
    omet
    0.86
    Activations Density 0.020%

    No Known Activations