© 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. 10-RES-JB
    11. 10201
    Prev
    Next
    INDEX
    Explanations

    words related to physical movement and action

    oai_token-act-pair · gpt-3.5-turbo

    numerical or quantified descriptions of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hner
    -0.67
    BuyableInstoreAndOnline
    -0.61
    oulos
    -0.58
    eteenth
    -0.57
     Alternatively
    -0.55
    ¶
    -0.54
    ivist
    -0.53
    terness
    -0.53
     ®
    -0.53
     Blasio
    -0.52
    POSITIVE LOGITS
     unbelievable
    0.93
     everything
    0.92
     everywhere
    0.92
     EVERY
    0.92
     alot
    0.90
     amazing
    0.90
     incredible
    0.89
     amazingly
    0.89
     tremendously
    0.87
     tremendous
    0.86
    Activations Density 1.267%

    No Known Activations