© 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. 20449
    Prev
    Next
    INDEX
    Explanations

    geographical locations or names containing "Tor" or "To", possibly related to sports or politics

    oai_token-act-pair · gpt-3.5-turbo

    patterns related to the city of Toronto

    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
    ruary
    -0.88
    abase
    -0.87
    anchester
    -0.78
    heit
    -0.67
    nyder
    -0.65
    arcity
    -0.60
    ëĭ
    -0.56
    abwe
    -0.56
    ateurs
    -0.56
    pard
    -0.56
    POSITIVE LOGITS
    ondo
    0.81
    thro
    0.71
    nic
    0.69
    agi
    0.67
    ©¶æ
    0.67
    ritic
    0.66
    intel
    0.64
     Shogun
    0.64
    INAL
    0.63
     Io
    0.63
    Activations Density 0.221%

    No Known Activations