© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 3246
    Prev
    Next
    INDEX
    Explanations

    abbreviations, model names, and technical features

    oai_token-act-pair · gpt-3.5-turbo

    products and technologies for portable electronics

    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
     redacted
    -0.83
    =-=-
    -0.76
    #$#$
    -0.75
     Edited
    -0.75
     Transcript
    -0.72
    hens
    -0.71
    insk
    -0.71
     dise
    -0.70
    staking
    -0.70
     Minor
    -0.69
    POSITIVE LOGITS
     gadget
    1.35
     gadgets
    1.33
     handheld
    1.26
     appliance
    1.26
     device
    1.26
     portable
    1.24
     devices
    1.24
     wearable
    1.24
     accessories
    1.22
     smartphone
    1.22
    Activations Density 0.538%

    No Known Activations