© 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. 7-RES-JB
    11. 11744
    Prev
    Next
    INDEX
    Explanations

    words related to financial matters, particularly payroll

    oai_token-act-pair · gpt-3.5-turbo

    terms related to employment and payroll

    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
    bol
    -0.89
    ago
    -0.83
    opol
    -0.78
    hered
    -0.77
    xual
    -0.77
    pire
    -0.74
    actionDate
    -0.74
    ulton
    -0.73
    heimer
    -0.72
    udic
    -0.70
    POSITIVE LOGITS
     payroll
    1.06
    s
    0.94
     deductions
    0.75
     taxes
    0.73
     accountant
    0.69
     rebate
    0.67
     tax
    0.65
     miracles
    0.65
     mixer
    0.64
     records
    0.63
    Activations Density 0.041%

    No Known Activations