© 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. 10-RES-JB
    11. 9225
    Prev
    Next
    INDEX
    Explanations

    mentions or references to pension-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to pension and retirement systems

    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
    selves
    -0.76
    iPhone
    -0.72
    canon
    -0.71
    stasy
    -0.67
    okin
    -0.67
    usalem
    -0.64
    ambers
    -0.63
    amber
    -0.62
    alogue
    -0.61
    blogs
    -0.61
    POSITIVE LOGITS
     pensions
    1.14
     pension
    1.09
     fund
    1.05
     payout
    1.02
     payments
    1.02
     entitle
    1.01
     Pension
    0.96
     payable
    0.96
     liabilities
    0.95
     funds
    0.91
    Activations Density 0.038%

    No Known Activations