© 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. 5186
    Prev
    Next
    INDEX
    Explanations

    specific components or parts within a system

    oai_token-act-pair · gpt-3.5-turbo

    components and parts related to mechanical and electronic systems

    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
    ADRA
    -0.77
    irgin
    -0.66
    isine
    -0.66
     Breed
    -0.66
     resurg
    -0.65
     Towns
    -0.65
    abouts
    -0.62
    Week
    -0.62
    Ļ½
    -0.62
    CAST
    -0.61
    POSITIVE LOGITS
     diameter
    1.08
     protr
    0.97
     nozzle
    0.84
     width
    0.84
     structure
    0.84
     compartment
    0.83
     attached
    0.82
     portion
    0.82
     protector
    0.81
     cavity
    0.81
    Activations Density 0.206%

    No Known Activations