© 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. 3-RES-JB
    11. 7245
    Prev
    Next
    INDEX
    Explanations

    domains and domain-related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of domain names

    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
    tics
    -0.77
     Clement
    -0.70
    eph
    -0.67
     Fulton
    -0.65
    tical
    -0.63
    EV
    -0.62
     Hayward
    -0.61
     Irving
    -0.60
    felt
    -0.60
     Dek
    -0.59
    POSITIVE LOGITS
     domain
    0.93
     domains
    0.91
    domain
    0.84
    izen
    0.83
    Domain
    0.78
    wcsstore
    0.78
     Domain
    0.77
     controller
    0.76
    llular
    0.75
     controllers
    0.74
    Activations Density 0.010%

    No Known Activations