© 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. 10-RES-JB
    11. 16953
    Prev
    Next
    INDEX
    Explanations

    words related to negative attributes or consequences

    oai_token-act-pair · gpt-3.5-turbo

    negative phrases related to health or unfavorable conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sharing
    -0.66
     rings
    -0.63
     Shooter
    -0.62
     Nope
    -0.61
     endlessly
    -0.61
    illon
    -0.60
     Rouge
    -0.60
    £ı
    -0.59
     Noir
    -0.59
    ulhu
    -0.58
    POSITIVE LOGITS
    gotten
    1.27
    fitting
    1.15
    equipped
    1.13
    founded
    1.10
    defined
    1.10
    treatment
    1.06
    informed
    1.04
    fortune
    0.98
    intent
    0.96
    treated
    0.96
    Activations Density 0.028%

    No Known Activations