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. 5399
    Prev
    Next
    INDEX
    Explanations

    mentions of shortages in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of shortages

    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
    Male
    -0.81
    ramid
    -0.74
    tips
    -0.71
    Auth
    -0.66
    gress
    -0.66
    Ocean
    -0.64
    missions
    -0.64
    20439
    -0.63
    Reviewer
    -0.63
    ophile
    -0.62
    POSITIVE LOGITS
     shortages
    0.96
     shortage
    0.85
     liquidity
    0.83
     plag
    0.82
     thereof
    0.76
     overrun
    0.72
    urrection
    0.72
    lust
    0.71
     glut
    0.71
     worsened
    0.70
    Activations Density 0.019%

    No Known Activations