© 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. 8-RES-JB
    11. 3862
    Prev
    Next
    INDEX
    Explanations

    action verbs related to communication and disclosure

    oai_token-act-pair · gpt-3.5-turbo

    actions related to stating or explaining information

    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
    agos
    -0.79
    avery
    -0.71
    ceans
    -0.71
    boot
    -0.69
    eries
    -0.68
    agues
    -0.68
    aspx
    -0.66
    enf
    -0.66
    ï¸ı
    -0.66
    cour
    -0.64
    POSITIVE LOGITS
     aloud
    1.03
     loudly
    0.94
     oneself
    0.88
     allegiance
    0.82
     anything
    0.82
     something
    0.80
     publicly
    0.78
     paternity
    0.77
     goodbye
    0.76
     wrongdoing
    0.76
    Activations Density 0.338%

    No Known Activations