© 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. 4-RES-JB
    11. 20900
    Prev
    Next
    INDEX
    Explanations

    references to car models and classes, specifically those related to GT versions

    oai_token-act-pair · gpt-3.5-turbo

    references to GT classifications in automobiles, particularly the Ferrari GT models

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

    No Comments

    Negative Logits
    ufact
    -0.98
    Downloadha
    -0.95
    ividual
    -0.71
    taining
    -0.70
    iotics
    -0.70
     Debor
    -0.69
     MSM
    -0.69
     Samoa
    -0.68
    die
    -0.68
    theless
    -0.68
    POSITIVE LOGITS
    TY
    0.85
    GT
    0.83
     GT
    0.79
    TER
    0.75
    amera
    0.74
    anooga
    0.74
    ravis
    0.73
    agne
    0.72
    RAY
    0.72
    het
    0.72
    Activations Density 0.010%

    No Known Activations