© 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. 7-RES-JB
    11. 1936
    Prev
    Next
    INDEX
    Explanations

    terms related to different ages or periods of time

    oai_token-act-pair · gpt-3.5-turbo

    timestamps indicating different societal or technological eras

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Yards
    -0.67
     promot
    -0.64
    KC
    -0.63
    summary
    -0.62
    mates
    -0.62
     bite
    -0.62
    arer
    -0.62
    ube
    -0.61
    ints
    -0.60
    cause
    -0.60
    POSITIVE LOGITS
     globalization
    0.84
     Orwell
    0.82
     technologically
    0.82
    industrial
    0.79
     climate
    0.79
     democracy
    0.77
     polarized
    0.76
     global
    0.75
     geop
    0.73
     democracies
    0.73
    Activations Density 0.278%

    No Known Activations