© 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. 0-RES-JB
    11. 12241
    Prev
    Next
    INDEX
    Explanations

    words related to the term "Turin"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Tur."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ournal
    -0.69
    gd
    -0.68
     booked
    -0.67
    erest
    -0.67
    YY
    -0.66
    expr
    -0.65
     reinvest
    -0.64
    elly
    -0.63
    ISON
    -0.63
     lick
    -0.63
    POSITIVE LOGITS
     Tur
    4.01
    Tur
    2.80
    tur
    2.01
     tur
    1.90
     turb
    1.40
     Turk
    1.36
     turrets
    1.25
     Turbo
    1.25
     Fer
    1.22
     Tor
    1.15
    Activations Density 0.015%

    No Known Activations