© 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. 1-RES-JB
    11. 3473
    Prev
    Next
    INDEX
    Explanations

    the name "Nelson"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities with the name "Ni."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dress
    -0.90
    drive
    -0.79
    rated
    -0.76
     Agents
    -0.71
    sharing
    -0.70
    dates
    -0.69
    stage
    -0.69
    eering
    -0.69
    spring
    -0.68
    Agent
    -0.68
    POSITIVE LOGITS
     Ni
    1.17
    agara
    0.97
    oko
    0.94
    uggets
    0.93
    Ni
    0.92
    ás
    0.91
    Ko
    0.90
    obi
    0.89
    omi
    0.88
    urnal
    0.87
    Activations Density 0.004%

    No Known Activations