© 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. 23934
    Prev
    Next
    INDEX
    Explanations

    keywords related to basic needs such as food, water, shelter, and medical supplies

    oai_token-act-pair · gpt-3.5-turbo

    references to essential resources like food, water, and shelter

    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
    ategory
    -0.85
    igmat
    -0.81
    eatures
    -0.72
    ynasty
    -0.69
    ahime
    -0.66
     reneg
    -0.65
     kinetic
    -0.65
    umn
    -0.65
     franch
    -0.64
     criminality
    -0.64
    POSITIVE LOGITS
     supplies
    1.22
     necessities
    1.08
     ration
    1.05
    Aid
    1.01
     essentials
    0.97
     allowance
    0.95
     staples
    0.95
     meals
    0.95
     blankets
    0.94
     shortages
    0.93
    Activations Density 0.223%

    No Known Activations