© 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. 8-RES-JB
    11. 1970
    Prev
    Next
    INDEX
    Explanations

    political and financial terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to political agendas and ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     extent
    -0.67
    Minor
    -0.63
    cknow
    -0.58
    pport
    -0.57
     upkeep
    -0.56
     arrang
    -0.55
     Wish
    -0.55
     Supported
    -0.52
    ALSE
    -0.52
    ording
    -0.51
    POSITIVE LOGITS
     onto
    1.80
     into
    1.64
    into
    1.37
     Into
    1.28
     INTO
    1.20
     toward
    1.02
     overboard
    0.99
     towards
    0.94
    onto
    0.92
     squarely
    0.89
    Activations Density 1.103%

    No Known Activations