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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 22650
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflict resolution or cessation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of ending or stopping something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     substr
    -0.64
    soDeliveryDate
    -0.63
    arted
    -0.63
     toile
    -0.62
     surfaces
    -0.62
    rients
    -0.61
    leans
    -0.60
    Catalog
    -0.60
    warts
    -0.59
     crest
    -0.58
    POSITIVE LOGITS
     hostilities
    1.10
     impunity
    1.06
     slavery
    0.98
     reliance
    0.97
     bloodshed
    0.97
     dependence
    0.96
    angering
    0.93
     discrimination
    0.91
     Prohibition
    0.86
     prohibition
    0.86
    Activations Density 0.112%

    No Known Activations