© 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. 17938
    Prev
    Next
    INDEX
    Explanations

    phrases indicating sufficiency or adequacy

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating sufficiency or adequacy

    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
    updated
    -0.63
     Moroccan
    -0.63
     Kenyan
    -0.61
     transmissions
    -0.60
    Bah
    -0.60
     Ghana
    -0.60
     Jama
    -0.60
     Shiva
    -0.60
    ãĥĨ
    -0.59
     synchronization
    -0.59
    POSITIVE LOGITS
     satisfy
    1.26
     justify
    1.18
     warrant
    1.16
     qualify
    1.14
     survive
    1.06
     withstand
    1.03
     earn
    1.00
     deserve
    1.00
     merit
    0.99
     allow
    0.99
    Activations Density 0.077%

    No Known Activations