© 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. 8-RES-JB
    11. 17749
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names related to politics or conflicts, particularly related to Mexico

    oai_token-act-pair · gpt-3.5-turbo

    specific occurrences or variations of the syllable "Mi" related to locations or names, particularly with a focus on Michoacán and associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    croft
    -0.66
     Marketable
    -0.63
     chamber
    -0.62
     berth
    -0.61
    bush
    -0.60
     Goose
    -0.57
     doors
    -0.57
    bed
    -0.57
    minecraft
    -0.56
    ength
    -0.56
    POSITIVE LOGITS
    士
    0.79
    д
    0.71
    Ĵ
    0.68
    arella
    0.66
     Manson
    0.64
    Semitic
    0.63
    itary
    0.63
    ippi
    0.63
    ————
    0.63
    Ĩ
    0.62
    Activations Density 0.261%

    No Known Activations