© 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. 1-RES-JB
    11. 16427
    Prev
    Next
    INDEX
    Explanations

    mentions of scarce or abundant resources

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scarcity and abundance of resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abad
    -0.72
    uyomi
    -0.68
    sein
    -0.68
    mes
    -0.67
    notations
    -0.67
    irlf
    -0.67
    ricular
    -0.65
    WAR
    -0.64
    ocene
    -0.63
    cair
    -0.62
    POSITIVE LOGITS
     scarce
    1.20
     plentiful
    0.87
    ãĤ©
    0.84
    ãĤ£
    0.83
     abundant
    0.83
    女
    0.77
     resources
    0.76
     scarcity
    0.74
     bount
    0.72
    \\\\
    0.72
    Activations Density 0.013%

    No Known Activations