© 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. 4-RES-JB
    11. 432
    Prev
    Next
    INDEX
    Explanations

    references to financial bills or expenses

    oai_token-act-pair · gpt-3.5-turbo

    references to financial obligations or expenses

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

    No Comments

    Negative Logits
     Flavoring
    -0.91
    rane
    -0.72
    onomous
    -0.68
    pmwiki
    -0.65
    reen
    -0.63
     Pv
    -0.63
    spect
    -0.63
    inction
    -0.63
     obser
    -0.62
    rity
    -0.61
    POSITIVE LOGITS
    iard
    1.36
    igan
    0.86
     bills
    0.81
    ings
    0.81
    hyde
    0.80
    owed
    0.77
    owing
    0.77
    book
    0.76
    papers
    0.76
    marks
    0.75
    Activations Density 0.023%

    No Known Activations