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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 15802
    Prev
    Next
    INDEX
    Explanations

    phrases related to intentional design or planning

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "designed" in various contexts related to purpose and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anon
    -0.72
    rika
    -0.70
     Michaels
    -0.61
    asta
    -0.60
    some
    -0.59
    yards
    -0.58
     tears
    -0.58
    talk
    -0.57
     Heard
    -0.57
    bour
    -0.57
    POSITIVE LOGITS
    urally
    0.82
    irection
    0.82
     Parenthood
    0.81
     expressly
    0.80
     designed
    0.80
    paren
    0.79
    designed
    0.78
    rador
    0.77
     specifically
    0.77
    ators
    0.76
    Activations Density 0.045%

    No Known Activations