© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9440
    Prev
    Next
    INDEX
    Explanations

    words related to the action of publishing something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the act of publishing

    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
    llan
    -0.88
    xa
    -0.75
    enhagen
    -0.73
    nea
    -0.71
    bones
    -0.70
    mer
    -0.69
    ugh
    -0.69
    phant
    -0.68
     awoken
    -0.66
     awakened
    -0.65
    POSITIVE LOGITS
    lishing
    1.21
    lisher
    1.06
     excerpts
    0.96
    lishes
    0.87
     publication
    0.79
     publishing
    0.78
     journal
    0.77
     journals
    0.76
     Journals
    0.75
     anonymously
    0.74
    Activations Density 0.054%

    No Known Activations