Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 7200
    Prev
    Next
    INDEX
    Explanations

    words related to income distribution, specifically highlighting the highest income quintile

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to income distribution and socioeconomic status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     patience
    -0.77
     Hydra
    -0.73
     interference
    -0.73
     waive
    -0.71
     maneuver
    -0.70
     motion
    -0.69
     routing
    -0.69
     aid
    -0.69
     equipment
    -0.67
     foam
    -0.67
    POSITIVE LOGITS
     socially
    1.66
     quint
    1.36
     Census
    1.27
     chromosomes
    1.24
     maternal
    1.23
     preval
    1.21
     socioeconomic
    1.20
     chromosome
    1.19
     behaviours
    1.17
     socio
    1.17
    Activations Density 0.065%

    No Known Activations