© 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. 6-RES-JB
    11. 284
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and governmental entities or positions

    oai_token-act-pair · gpt-3.5-turbo

    references to political entities and figures

    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
     traumatic
    -0.70
    iannopoulos
    -0.70
     forestry
    -0.67
     dent
    -0.66
     tourism
    -0.63
     skiing
    -0.62
     guiActiveUn
    -0.62
    SPONSORED
    -0.61
     autism
    -0.61
     yoga
    -0.60
    POSITIVE LOGITS
     Accountability
    0.97
     Himself
    0.95
    swer
    0.94
     Graveyard
    0.90
     Characters
    0.89
     Party
    0.87
     Manager
    0.86
     Representatives
    0.85
     Purpose
    0.84
     Builder
    0.84
    Activations Density 0.268%

    No Known Activations