© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20818
    Prev
    Next
    INDEX
    Explanations

    phrases related to potential risks or negative outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express potential or likelihood regarding events or situations

    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
    minus
    -0.91
    é¾įåĸļ士
    -0.87
    icator
    -0.85
    arte
    -0.84
    rand
    -0.82
    Favorite
    -0.80
     Originally
    -0.80
    idelines
    -0.79
    maxwell
    -0.79
    mbuds
    -0.78
    POSITIVE LOGITS
     disruption
    1.27
     disruptions
    1.15
     landsl
    1.14
     repr
    1.14
     upheaval
    1.12
     retaliation
    1.11
     repercussions
    1.10
     retribution
    1.10
     duplication
    1.10
     layoffs
    1.09
    Activations Density 0.193%

    No Known Activations