© 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 EvalsExportsinterp-engineNEWAPI 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. 23321
    Prev
    Next
    INDEX
    Explanations

    instances of text that mention or relate to JSON objects or data format

    oai_token-act-pair · gpt-3.5-turbo

    references to JSON data structure and type in programming contexts

    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
    ndra
    -1.04
    neau
    -0.81
    agonist
    -0.81
    noxious
    -0.75
    udder
    -0.74
    hra
    -0.74
    arios
    -0.73
    arak
    -0.73
    mans
    -0.72
    ammy
    -0.71
    POSITIVE LOGITS
     encoded
    1.30
     encoding
    1.29
     formatted
    1.21
     liter
    1.20
     format
    1.11
     representation
    1.10
     literal
    1.09
     parsing
    1.09
     representations
    1.09
    UTF
    1.09
    Activations Density 0.146%

    No Known Activations