© 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. 6-RES-JB
    11. 20466
    Prev
    Next
    INDEX
    Explanations

    words related to fiscal matters or financial issues

    oai_token-act-pair · gpt-3.5-turbo

    references to fiscal years and budget discussions

    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
    ipedia
    -0.82
     Cosponsors
    -0.78
    lain
    -0.76
    posts
    -0.73
    hin
    -0.72
    vu
    -0.70
    skirts
    -0.70
     Brist
    -0.70
     Jem
    -0.70
    ichen
    -0.69
    POSITIVE LOGITS
     restraint
    0.83
     deficits
    0.79
     consolidation
    0.74
     warfare
    0.74
     overflow
    0.74
     cliff
    0.73
     austerity
    0.73
     conservatism
    0.73
     tract
    0.73
     deficit
    0.72
    Activations Density 0.015%

    No Known Activations