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. 4-RES-JB
    6. 8421
    Prev
    Next
    INDEX
    Explanations

    terms related to social entitlement and government entitlement programs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to entitlement and associated concepts

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

    No Comments

    Negative Logits
    hematic
    -0.73
     Fiber
    -0.67
     Archangel
    -0.67
    apest
    -0.66
    olin
    -0.66
    rawling
    -0.65
     Edison
    -0.64
    ician
    -0.62
    ucket
    -0.62
    ector
    -0.61
    POSITIVE LOGITS
     entitle
    1.39
     entitlement
    1.04
     beneficiaries
    0.94
     entit
    0.90
     privileges
    0.79
     recipients
    0.76
    eals
    0.75
     obligations
    0.74
     clearance
    0.74
     granted
    0.73
    Activations Density 0.005%

    No Known Activations