© 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. 14628
    Prev
    Next
    INDEX
    Explanations

    references to events or actions happening

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "came."

    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
    olor
    -0.82
    ignty
    -0.75
    ²¾
    -0.72
    benefit
    -0.72
    guided
    -0.71
    raid
    -0.70
    orthodox
    -0.69
    ycle
    -0.68
    rendered
    -0.68
    relevant
    -0.68
    POSITIVE LOGITS
     undone
    1.09
     ashore
    0.91
     forth
    0.83
     crashing
    0.82
     roaring
    0.81
     pouring
    0.80
     flooding
    0.77
     out
    0.74
     closer
    0.73
     Forth
    0.71
    Activations Density 0.065%

    No Known Activations