© 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. 8-RES-JB
    11. 6928
    Prev
    Next
    INDEX
    Explanations

    numerical values related to income and money

    oai_token-act-pair · gpt-3.5-turbo

    financial statistics related to income and earnings

    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
     reinforcements
    -0.75
     reviewers
    -0.72
     reviewer
    -0.70
     shipment
    -0.68
     Collider
    -0.68
     replay
    -0.68
     Airl
    -0.67
     redund
    -0.67
     synergy
    -0.67
     precaution
    -0.66
    POSITIVE LOGITS
     percentile
    0.91
     median
    0.86
    overty
    0.84
     liv
    0.84
     incomes
    0.83
     poverty
    0.83
    ilege
    0.81
     bachelor
    0.80
     subsistence
    0.80
     income
    0.80
    Activations Density 0.277%

    No Known Activations