© 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. 16829
    Prev
    Next
    INDEX
    Explanations

    terms related to a large quantity or variety of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the special end-of-text token

    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
    ional
    -0.90
    endi
    -0.87
    inates
    -0.82
    ives
    -0.81
    ively
    -0.80
    essee
    -0.79
    ior
    -0.78
    ians
    -0.78
    agers
    -0.75
    inators
    -0.75
    POSITIVE LOGITS
    ï¸ı
    0.77
    theless
    0.73
    tons
    0.72
    hog
    0.68
    BOOK
    0.68
    Posted
    0.68
    tle
    0.66
    ffe
    0.66
     Ascend
    0.65
    tal
    0.63
    Activations Density 0.091%

    No Known Activations