© 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. 9-RES-JB
    11. 2008
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or governmental actions

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "by" in various contexts, indicating actions or attributions

    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
    bian
    -0.74
    bard
    -0.71
    raq
    -0.70
    heimer
    -0.70
    edin
    -0.68
    hene
    -0.67
    bach
    -0.67
    ivia
    -0.65
    atem
    -0.65
    pal
    -0.65
    POSITIVE LOGITS
     virtue
    1.39
    products
    1.13
    gone
    1.01
     omission
    0.97
     implication
    0.97
    laws
    0.96
     proxy
    0.90
     means
    0.89
     default
    0.86
     invoking
    0.83
    Activations Density 0.145%

    No Known Activations