© 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 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. 3-RES-JB
    11. 3500
    Prev
    Next
    INDEX
    Explanations

    references to specific technical terms or product names

    oai_token-act-pair · gpt-3.5-turbo

    designations and classifications related to specific types of substances or products

    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
     Ukrainians
    -0.78
    esville
    -0.78
    ropolitan
    -0.73
    riad
    -0.72
    oise
    -0.71
    ique
    -0.70
    iary
    -0.69
    roit
    -0.69
    gdala
    -0.68
    makers
    -0.67
    POSITIVE LOGITS
    andom
    0.94
    ategy
    0.93
    adish
    0.87
    addle
    0.87
    senal
    0.86
    idge
    0.86
    uth
    0.86
    uler
    0.84
    ifter
    0.84
    aditional
    0.84
    Activations Density 0.007%

    No Known Activations