© 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. 1-RES-JB
    11. 23570
    Prev
    Next
    INDEX
    Explanations

    terms related to financial planning and savings for retirement

    oai_token-act-pair · gpt-3.5-turbo

    mentions of retirement and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    internal
    -0.70
    ean
    -0.68
    Grab
    -0.68
    %]
    -0.67
    slaught
    -0.67
    Magikarp
    -0.67
    iPhone
    -0.66
    mic
    -0.66
    asp
    -0.66
    inx
    -0.65
    POSITIVE LOGITS
     retirement
    1.13
     Retirement
    0.98
     retire
    0.97
     retiring
    0.89
     pensions
    0.84
    spective
    0.79
     srfAttach
    0.77
     Skydragon
    0.76
     pension
    0.75
     lounge
    0.71
    Activations Density 0.008%

    No Known Activations