© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 9868
    Prev
    Next
    INDEX
    Explanations

    mentions of financial transactions or legal agreements, specifically focusing on the term 'dues' or 'ratified'

    oai_token-act-pair · gpt-3.5-turbo

    references to union dues and legislative ratification processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Notting
    -0.80
    Plex
    -0.80
    flush
    -0.77
     briefing
    -0.75
     BBC
    -0.71
     Kens
    -0.69
    Pic
    -0.68
     Kit
    -0.67
     Kop
    -0.67
     Ashes
    -0.67
    POSITIVE LOGITS
     dues
    2.28
     ratified
    1.68
     Legisl
    1.44
     legislator
    1.42
     legislators
    1.35
     ALEC
    1.30
     prohibit
    1.21
     rescind
    1.20
    laws
    1.19
     ratification
    1.11
    Activations Density 0.058%

    No Known Activations