© 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. 6-RES-JB
    11. 17123
    Prev
    Next
    INDEX
    Explanations

    words related to financial payment terms and business operations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to payroll and tax information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uart
    -0.73
    olog
    -0.73
    opol
    -0.71
    igo
    -0.66
    ago
    -0.66
    ulton
    -0.64
     Orthodox
    -0.64
    anton
    -0.63
    CONCLUS
    -0.63
    bol
    -0.63
    POSITIVE LOGITS
     payroll
    1.19
     taxes
    0.94
     deductions
    0.89
     earners
    0.83
     tax
    0.82
     payable
    0.79
     dues
    0.79
     rebate
    0.77
     accountant
    0.76
    s
    0.76
    Activations Density 0.010%

    No Known Activations