© 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. 1939
    Prev
    Next
    INDEX
    Explanations

    references to the sports team "Villa," likely referring to Aston Villa football club

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Villa," particularly in a context related to sports or events associated with Aston Villa

    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
    ded
    -0.92
    eln
    -0.92
    hip
    -0.88
    lers
    -0.86
    daq
    -0.85
    rift
    -0.84
    stro
    -0.84
    */(
    -0.82
    geon
    -0.81
    hips
    -0.81
    POSITIVE LOGITS
    ocally
    0.76
    ipes
    0.67
     Dame
    0.67
    irie
    0.67
    zzo
    0.67
     Scotia
    0.66
     Rica
    0.65
     syrup
    0.64
     Vie
    0.63
    ño
    0.62
    Activations Density 0.069%

    No Known Activations