Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 21463
    Prev
    Next
    INDEX
    Explanations

    terms related to financial allowances and expenses

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial allowances and expenditures

    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
    ravis
    -0.68
    tra
    -0.66
     Gang
    -0.65
    inx
    -0.61
    ific
    -0.61
    pack
    -0.61
     bite
    -0.61
     Wichita
    -0.60
    act
    -0.59
    raz
    -0.58
    POSITIVE LOGITS
     allowances
    1.21
     allowance
    1.16
    ments
    0.93
     exemptions
    0.89
     deductions
    0.81
    Ĥª
    0.80
     holders
    0.79
    ary
    0.77
    folios
    0.76
     balances
    0.76
    Activations Density 0.011%

    No Known Activations