© 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. 8-RES-JB
    11. 2404
    Prev
    Next
    INDEX
    Explanations

    phrases related to running out of resources or supplies

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating depletion or shortage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.68
    ciplinary
    -0.68
    ŃĶ
    -0.66
     obscured
    -0.63
    pillar
    -0.62
     statically
    -0.62
    violent
    -0.61
    soc
    -0.61
    hemy
    -0.61
    edi
    -0.60
    POSITIVE LOGITS
     patience
    0.93
     supplies
    0.79
     excuses
    0.79
    ãĤ¨ãĥ«
    0.73
     funds
    0.71
    bos
    0.70
     resources
    0.70
     gallons
    0.69
     adject
    0.68
    urdue
    0.68
    Activations Density 0.077%

    No Known Activations