© 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. 3-RES-JB
    11. 15248
    Prev
    Next
    INDEX
    Explanations

    words related to public utilities

    oai_token-act-pair · gpt-3.5-turbo

    references to utility services

    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
    eworld
    -0.85
    orne
    -0.84
    uten
    -0.84
    oning
    -0.83
    bring
    -0.83
    thus
    -0.82
    artisan
    -0.82
    ago
    -0.77
    reads
    -0.77
    ellen
    -0.75
    POSITIVE LOGITS
     utility
    1.05
     utilities
    1.03
    PDATE
    0.85
     Utilities
    0.84
    gency
    0.81
     subst
    0.80
     nomine
    0.78
    ilities
    0.78
     manag
    0.77
    stration
    0.76
    Activations Density 0.010%

    No Known Activations