© 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. 9-RES-JB
    11. 17760
    Prev
    Next
    INDEX
    Explanations

    mentions of negative factors like poor conditions, performance, or oversight

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with inadequate conditions or poor performance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ften
    -0.83
    roo
    -0.82
     angrily
    -0.81
    udder
    -0.74
     CLSID
    -0.73
     Enabled
    -0.72
    emonium
    -0.72
    Ru
    -0.71
    LESS
    -0.70
    ultimate
    -0.69
    POSITIVE LOGITS
     performance
    1.09
     rainfall
    1.04
     connectivity
    1.03
     demographics
    1.01
     communication
    1.00
     availability
    1.00
     enrollment
    1.00
     attendance
    0.99
     finances
    0.97
     governance
    0.97
    Activations Density 0.273%

    No Known Activations