© 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. 0-RES-JB
    11. 16380
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial expenses

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rap
    -0.74
    olk
    -0.70
     Preview
    -0.69
     hardened
    -0.65
     binary
    -0.64
     paired
    -0.63
    yi
    -0.62
    rig
    -0.62
    reg
    -0.62
     laced
    -0.61
    POSITIVE LOGITS
     expenses
    3.59
     expense
    2.37
     costs
    2.12
     expenditures
    2.04
     fees
    1.76
     Costs
    1.73
     expenditure
    1.69
     debts
    1.57
     liabilities
    1.51
     reimburse
    1.47
    Activations Density 0.017%

    No Known Activations