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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 23417
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations or groups of people

    oai_token-act-pair · gpt-3.5-turbo

    prominent nouns and specific terms related to movements or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ctica
    -0.71
    etheless
    -0.69
    myra
    -0.65
    ãģĤ
    -0.65
    imeters
    -0.65
    ¶æ
    -0.64
    adapt
    -0.63
    ĻĤ
    -0.63
     manag
    -0.60
     compr
    -0.59
    POSITIVE LOGITS
     Era
    1.05
     Initiative
    1.02
     Collection
    1.01
     Consortium
    0.99
     Awards
    0.98
     Agreement
    0.96
     Institute
    0.94
    âĦ¢
    0.93
     Project
    0.91
     Tribunal
    0.91
    Activations Density 0.411%

    No Known Activations