© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5025
    Prev
    Next
    INDEX
    Explanations

    locations or entities associated with the word "ring"

    oai_token-act-pair · gpt-3.5-turbo

    words related to rings or circular shapes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ultz
    -0.82
    mson
    -0.67
    ufact
    -0.67
    merce
    -0.66
    ossession
    -0.65
    EMP
    -0.63
    uliffe
    -0.63
    ACP
    -0.63
    grown
    -0.62
    isable
    -0.61
    POSITIVE LOGITS
    naire
    0.94
    bone
    0.93
    tons
    0.89
    naires
    0.89
    tone
    0.87
    er
    0.87
    rings
    0.86
    ettes
    0.86
    ette
    0.85
    maid
    0.84
    Activations Density 0.022%

    No Known Activations