© 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. 7-RES-JB
    11. 12677
    Prev
    Next
    INDEX
    Explanations

    passive verbs related to development or creation

    oai_token-act-pair · gpt-3.5-turbo

    words related to the development and production of various items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.72
    ãģĦ
    -0.70
    drop
    -0.69
     Carbuncle
    -0.68
    ede
    -0.63
    SPONSORED
    -0.62
    talk
    -0.61
    bro
    -0.60
    ogle
    -0.59
    inventoryQuantity
    -0.58
    POSITIVE LOGITS
     collabor
    1.01
     by
    0.83
     independently
    0.76
     anew
    0.76
     jointly
    0.74
     entirely
    0.73
     principally
    0.71
    sterdam
    0.69
     exclusively
    0.68
     Seym
    0.68
    Activations Density 0.187%

    No Known Activations