© 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. 12541
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases followed by the word 'risk'

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote risk or concern regarding various topics

    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
    abase
    -0.90
    minus
    -0.77
     ILCS
    -0.76
    ortment
    -0.75
    uid
    -0.70
    nice
    -0.70
    issance
    -0.70
    ele
    -0.68
    ritz
    -0.68
    imil
    -0.67
    POSITIVE LOGITS
     retribution
    0.90
     impending
    0.83
     retaliation
    0.76
     congestion
    0.73
     uncertainties
    0.72
     disrupting
    0.72
     harming
    0.72
     repercussions
    0.72
     lingering
    0.71
     ruining
    0.69
    Activations Density 0.383%

    No Known Activations