© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 12962
    Prev
    Next
    INDEX
    Explanations

    words related to calmness or peace

    oai_token-act-pair · gpt-3.5-turbo

    references to "place" or "placement" concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ichick
    -0.82
    ns
    -0.64
     Exchange
    -0.63
    huge
    -0.62
     Patriots
    -0.62
     Myster
    -0.62
     Receiver
    -0.60
     Authentication
    -0.60
    ighter
    -0.59
    AAF
    -0.59
    POSITIVE LOGITS
     plac
    4.22
     placement
    1.49
     appe
    1.12
     pac
    1.10
     plat
    1.04
     appease
    0.94
     banners
    0.90
     diplom
    0.88
     lect
    0.88
     plaque
    0.83
    Activations Density 0.009%

    No Known Activations