© 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. 1-RES-JB
    11. 22527
    Prev
    Next
    INDEX
    Explanations

    instances of the city name "Birmingham."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to the city of Birmingham

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sth
    -0.80
    entially
    -0.76
    oward
    -0.76
    ivot
    -0.75
    ential
    -0.74
    afort
    -0.73
    cess
    -0.71
    uality
    -0.69
    OPLE
    -0.68
    ledged
    -0.66
    POSITIVE LOGITS
    mingham
    1.26
     Birmingham
    0.92
    ãĤ¦ãĤ¹
    0.82
    mouth
    0.82
    thouse
    0.81
     Blitz
    0.77
     accents
    0.77
    anooga
    0.76
    ©¶æ¥µ
    0.74
    ãĥ³ãĤ¸
    0.73
    Activations Density 0.002%

    No Known Activations