© 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. 3-RES-JB
    11. 23785
    Prev
    Next
    INDEX
    Explanations

    financial terms related to balancing accounts or budgets

    oai_token-act-pair · gpt-3.5-turbo

    references to financial or numerical balances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ABE
    -0.76
    Dur
    -0.68
    Assembly
    -0.68
     Cosponsors
    -0.67
    advertising
    -0.67
     Famous
    -0.64
    PLIC
    -0.64
    FER
    -0.63
    OLOG
    -0.62
    ————
    -0.61
    POSITIVE LOGITS
    balance
    1.15
     balance
    1.09
     balances
    1.06
     imbalance
    1.01
    balanced
    0.95
     Balance
    0.86
     balancing
    0.80
    weights
    0.79
    ament
    0.78
    opian
    0.77
    Activations Density 0.008%

    No Known Activations