© 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. 10444
    Prev
    Next
    INDEX
    Explanations

    terms related to government agencies or services

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental or public services

    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
    umin
    -0.74
    orn
    -0.74
    20439
    -0.71
    yle
    -0.69
    luaj
    -0.68
    arest
    -0.68
    ussen
    -0.65
    romeda
    -0.65
    åĮ
    -0.64
    ox
    -0.64
    POSITIVE LOGITS
     Employees
    1.11
     Provider
    1.10
     Service
    1.09
     Corps
    0.84
     Animals
    0.83
     Agent
    0.83
     Dogs
    0.82
     Services
    0.80
     Officers
    0.79
     Advis
    0.78
    Activations Density 0.012%

    No Known Activations