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. 10-RES-JB
    6. 19524
    Prev
    Next
    INDEX
    Explanations

    information related to financial assistance programs and pension changes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to social assistance programs and pension benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mosqu
    -0.98
    Ú
    -0.85
    flame
    -0.79
    Buzz
    -0.78
    roma
    -0.77
    Camera
    -0.76
     localization
    -0.76
     louder
    -0.75
    Pixel
    -0.75
     blasp
    -0.74
    POSITIVE LOGITS
     pensions
    1.66
     retirement
    1.63
     pension
    1.59
     retirees
    1.57
     Pension
    1.53
     Retirement
    1.52
     disability
    1.46
     entitle
    1.43
     Medicare
    1.42
     Disability
    1.40
    Activations Density 0.342%

    No Known Activations