© 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. 17054
    Prev
    Next
    INDEX
    Explanations

    terms related to demographic trends, such as generational groups and economic shifts

    oai_token-act-pair · gpt-3.5-turbo

    trends and behaviors of specific generational groups

    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
     Investigator
    -0.77
     ACLU
    -0.75
     Transgender
    -0.75
     Ethics
    -0.70
     Scientology
    -0.68
     Karma
    -0.68
     redacted
    -0.67
     Autism
    -0.67
     controversy
    -0.66
     Garfield
    -0.66
    POSITIVE LOGITS
     wealthier
    1.05
     poorer
    0.93
     cheaper
    0.90
     fewer
    0.86
     surplus
    0.83
     incomes
    0.82
     increasingly
    0.82
     affluent
    0.82
     richer
    0.81
     unemployed
    0.80
    Activations Density 1.184%

    No Known Activations