© 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. 2-RES-JB
    11. 12063
    Prev
    Next
    INDEX
    Explanations

    mentions of large quantities or sums of money

    oai_token-act-pair · gpt-3.5-turbo

    references to large quantities or populations of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Adv
    -0.77
    imen
    -0.70
    cial
    -0.67
    Sac
    -0.63
    mentioned
    -0.63
    cade
    -0.63
    mon
    -0.63
    chron
    -0.63
    occup
    -0.62
    aign
    -0.62
    POSITIVE LOGITS
     millions
    0.94
     Millions
    0.90
     billions
    0.88
     dollars
    0.88
     ILCS
    0.85
     lashes
    0.79
    ousands
    0.75
    aires
    0.73
     litres
    0.73
     Downloads
    0.71
    Activations Density 0.024%

    No Known Activations