© 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. 0-RES-JB
    11. 8305
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or terms, such as "Vlad", "omni", "repe", and "Bain"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names and terms associated with conflict and legislation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    essional
    -0.82
    REE
    -0.80
     Jets
    -0.78
    reek
    -0.77
    WER
    -0.75
    offic
    -0.73
    FOX
    -0.72
    ricular
    -0.72
     NOTICE
    -0.72
    âĢ¢
    -0.67
    POSITIVE LOGITS
     Vlad
    2.72
     omn
    1.35
     repe
    1.29
     Bain
    1.27
     Vox
    1.21
     Cathy
    1.17
     Omn
    1.10
     Nate
    1.05
     Zam
    1.05
    Cass
    1.02
    Activations Density 0.059%

    No Known Activations