© 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. 3636
    Prev
    Next
    INDEX
    Explanations

    items or actions related to emergency preparation

    oai_token-act-pair · gpt-3.5-turbo

    items and contents relevant to emergency preparedness

    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
    philis
    -0.80
     Seym
    -0.80
     Archdemon
    -0.77
    Hz
    -0.76
     Johann
    -0.75
     Cosponsors
    -0.75
    Graph
    -0.75
    yrights
    -0.74
     Griffith
    -0.73
    akespeare
    -0.73
    POSITIVE LOGITS
     bags
    1.76
     luggage
    1.74
     bag
    1.67
     backpack
    1.67
     suitcase
    1.61
     pouch
    1.48
     stash
    1.44
    uggage
    1.43
     compartment
    1.39
     baggage
    1.39
    Activations Density 0.508%

    No Known Activations