© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6949
    Prev
    Next
    INDEX
    Explanations

    phrases related to government welfare programs and benefits

    oai_token-act-pair · gpt-3.5-turbo

    terms related to government assistance programs and financial aid

    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
     Atmosp
    -0.75
    çīĪ
    -0.73
    Ul
    -0.73
    Gamer
    -0.73
    Temperature
    -0.72
    Sensor
    -0.71
    Engineers
    -0.71
    ãĤ¨ãĥ«
    -0.70
    ÃĽ
    -0.69
    ãĥ´
    -0.69
    POSITIVE LOGITS
     recipients
    1.27
     entitle
    1.24
     eligibility
    1.21
     beneficiaries
    1.12
     vouchers
    1.12
     Disability
    1.11
    elfare
    1.10
     rebate
    1.06
     entitlement
    1.06
     disability
    1.04
    Activations Density 0.238%

    No Known Activations