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

    Neuronpedia

    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. 9-RES-JB
    11. 3245
    Prev
    Next
    INDEX
    Explanations

    phrases related to government policies and tax reforms

    oai_token-act-pair · gpt-3.5-turbo

    discussions about political strategies and planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Inquisition
    -0.78
     +/-
    -0.72
     incident
    -0.72
    availability
    -0.72
    DragonMagazine
    -0.71
     TTL
    -0.70
    ĸļ
    -0.69
     nerves
    -0.68
    ilial
    -0.68
     Gate
    -0.67
    POSITIVE LOGITS
     proposals
    1.21
     bipartisan
    1.17
    Republicans
    1.11
     Republicans
    1.10
     repeal
    1.09
     propose
    1.08
     proposes
    1.08
     proposing
    1.07
     proposal
    1.05
     repealing
    1.04
    Activations Density 1.189%

    No Known Activations