© 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. 7-RES-JB
    11. 23922
    Prev
    Next
    INDEX
    Explanations

    locations or entities related to Birmingham

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Birmingham

    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
    apon
    -0.79
     Leilan
    -0.77
    erm
    -0.72
    afort
    -0.71
    iesel
    -0.71
    cedented
    -0.71
    cient
    -0.70
    orc
    -0.70
    imates
    -0.68
    iverse
    -0.68
    POSITIVE LOGITS
    mingham
    1.15
    ãĤ¦ãĤ¹
    0.79
    poons
    0.78
    ç·
    0.76
    bie
    0.75
    bing
    0.75
    keley
    0.74
    ãĥŁ
    0.71
    shire
    0.71
    ãĥĥãĤ¯
    0.71
    Activations Density 0.065%

    No Known Activations