© 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. 7-RES-JB
    11. 23485
    Prev
    Next
    INDEX
    Explanations

    mentions of financial expenses or costs

    oai_token-act-pair · gpt-3.5-turbo

    references to financial costs or expenditures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unin
    -0.85
    ezvous
    -0.82
    redd
    -0.79
    gewater
    -0.73
    azes
    -0.72
    IPS
    -0.72
    kus
    -0.68
    erd
    -0.67
    erk
    -0.65
    ĨĴ
    -0.65
    POSITIVE LOGITS
     incurred
    1.43
     expenses
    1.00
     reimburse
    0.99
     reimbursement
    0.91
     reimb
    0.90
     expense
    0.88
     expenditure
    0.86
    itures
    0.85
     expenditures
    0.83
    iture
    0.79
    Activations Density 0.023%

    No Known Activations