© 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. 0-RES-JB
    11. 14728
    Prev
    Next
    INDEX
    Explanations

    phrases related to wolves

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Wolves" and references related to bones or bone injuries

    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
     Cert
    -0.79
     ang
    -0.74
    aum
    -0.72
    aird
    -0.70
     iod
    -0.69
     certs
    -0.68
     declass
    -0.67
     resil
    -0.67
    irit
    -0.66
     beam
    -0.66
    POSITIVE LOGITS
     Wolves
    3.22
     Wiggins
    1.40
    knit
    1.28
    ippi
    1.22
    bones
    1.16
     Timberwolves
    1.09
    bone
    1.04
     Slovenia
    1.02
     FSA
    1.02
     Bent
    1.02
    Activations Density 0.042%

    No Known Activations