© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 15989
    Prev
    Next
    INDEX
    Explanations

    phrases related to labels and branding

    oai_token-act-pair · gpt-3.5-turbo

    references to product or brand labels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Remastered
    -0.71
    ashington
    -0.67
    olars
    -0.67
    vati
    -0.66
    abama
    -0.66
    nesota
    -0.64
     Tsu
    -0.63
    ================================================================
    -0.63
    thia
    -0.62
    enty
    -0.61
    POSITIVE LOGITS
     label
    1.06
     labels
    0.96
    label
    0.85
    mate
    0.84
    mates
    0.84
    furt
    0.82
    Label
    0.80
    ovan
    0.80
     Label
    0.78
    ifier
    0.77
    Activations Density 0.011%

    No Known Activations