© 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. 11306
    Prev
    Next
    INDEX
    Explanations

    phrases related to increasing or raising something

    oai_token-act-pair · gpt-3.5-turbo

    references to possession or ownership

    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
    mire
    -1.07
    ocument
    -0.74
     Canaver
    -0.73
    wic
    -0.72
    ollow
    -0.72
    ublic
    -0.70
    iors
    -0.69
    atcher
    -0.69
    Site
    -0.68
    ouse
    -0.68
    POSITIVE LOGITS
     own
    1.32
     chances
    1.28
     stature
    1.16
     ability
    1.15
     footprint
    1.11
     reliance
    1.09
     arsenal
    1.07
     susceptibility
    1.06
     productivity
    1.06
     capacity
    1.04
    Activations Density 0.142%

    No Known Activations