© 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. 4-RES-JB
    11. 21999
    Prev
    Next
    INDEX
    Explanations

    words related to the entity or concept of "Discovery."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Discovery" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arching
    -0.82
    iths
    -0.80
    uckles
    -0.77
    hovah
    -0.70
    etimes
    -0.69
    ework
    -0.69
    orically
    -0.69
    oiler
    -0.69
    ufact
    -0.68
    uffs
    -0.66
    POSITIVE LOGITS
     Discovery
    1.08
     Channel
    1.05
    Link
    0.84
     Journalism
    0.79
     Networks
    0.78
    Channel
    0.77
    gence
    0.76
    Flags
    0.76
     Communications
    0.75
    Network
    0.73
    Activations Density 0.007%

    No Known Activations