© 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. 17238
    Prev
    Next
    INDEX
    Explanations

    keywords related to observations and analysis such as "glance", "inspection", and "examination"

    oai_token-act-pair · gpt-3.5-turbo

    references to examination or observation

    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
     disadvantage
    -0.69
    cussion
    -0.64
     extinction
    -0.63
    iability
    -0.62
    icably
    -0.62
     urgency
    -0.61
     permanently
    -0.61
     contingency
    -0.61
     punishing
    -0.61
     reimb
    -0.61
    POSITIVE LOGITS
     glance
    1.04
     glances
    0.95
     google
    0.84
     browsing
    0.79
     pse
    0.78
     curs
    0.74
     Leaf
    0.71
    earcher
    0.71
     browse
    0.71
    ../
    0.70
    Activations Density 0.710%

    No Known Activations