© 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. 6-RES-JB
    11. 12114
    Prev
    Next
    INDEX
    Explanations

    events or milestones related to a person's first appearances or achievements in public contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant events or appearances in various contexts

    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
    isson
    -0.73
     abound
    -0.73
    ensional
    -0.64
    icter
    -0.63
     Bris
    -0.62
     Mund
    -0.62
     Jerome
    -0.61
    orius
    -0.60
     oneself
    -0.60
    ensor
    -0.59
    POSITIVE LOGITS
     outing
    1.01
    Ever
    0.91
     EVER
    0.90
     foray
    0.90
     ever
    0.83
     outings
    0.79
     appearance
    0.75
    mates
    0.73
     counterparts
    0.72
    IAS
    0.71
    Activations Density 0.353%

    No Known Activations