© 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. 4652
    Prev
    Next
    INDEX
    Explanations

    phrases related to different stages of growth or development

    oai_token-act-pair · gpt-3.5-turbo

    references to different phases or levels in processes

    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
    tymology
    -0.70
    vernment
    -0.67
    eros
    -0.66
    riad
    -0.63
    uala
    -0.63
    undai
    -0.62
     yawn
    -0.62
    vertisement
    -0.60
    vironment
    -0.60
    anguages
    -0.60
    POSITIVE LOGITS
    craft
    0.93
     stages
    0.89
    stage
    0.87
     stage
    0.85
    Stage
    0.82
    camp
    0.69
    ivals
    0.69
     Stage
    0.68
     Sabha
    0.68
    NetMessage
    0.67
    Activations Density 0.012%

    No Known Activations