© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 23913
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations and names, specifically "Preston" and "Plymouth"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific geographical locations and names, particularly "Preston" and "Plymouth."

    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
    dar
    -0.71
     defe
    -0.70
     thirds
    -0.70
     coh
    -0.69
    quished
    -0.68
    omes
    -0.66
    abc
    -0.65
    UGH
    -0.64
    ~~~~
    -0.64
     variables
    -0.63
    POSITIVE LOGITS
    sylvania
    0.91
    ople
    0.88
    etsk
    0.86
    roleum
    0.82
    cia
    0.81
    etry
    0.80
    ilon
    0.79
    sburgh
    0.78
    oshenko
    0.77
    rontal
    0.75
    Activations Density 0.026%

    No Known Activations