© 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. 6398
    Prev
    Next
    INDEX
    Explanations

    phrases related to potential outcomes or events

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements related to significant events or actions

    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
     liking
    -0.74
    eon
    -0.68
     prefers
    -0.66
     contracted
    -0.65
     crawling
    -0.65
    available
    -0.65
     sweats
    -0.65
     replies
    -0.65
    bugs
    -0.65
    running
    -0.64
    POSITIVE LOGITS
     usher
    1.16
     pave
    1.14
     signify
    1.10
     mark
    1.09
     herald
    1.08
     overturn
    1.08
     embold
    1.04
     vind
    1.04
     cement
    0.99
     jeopard
    0.99
    Activations Density 0.330%

    No Known Activations