© 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. 2-RES-JB
    11. 13785
    Prev
    Next
    INDEX
    Explanations

    references to wolves

    oai_token-act-pair · gpt-3.5-turbo

    references to wolves or wolf-like characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NAS
    -0.88
    angan
    -0.78
    graded
    -0.74
    dos
    -0.73
    arters
    -0.73
    mediate
    -0.72
    adian
    -0.71
    udos
    -0.70
    ursed
    -0.70
    claimed
    -0.69
    POSITIVE LOGITS
     wolves
    1.27
     wolf
    1.12
     Fenrir
    1.02
    wolves
    0.99
     Wolves
    0.93
    gang
    0.89
    hound
    0.86
    wolf
    0.86
     spiders
    0.80
    enstein
    0.80
    Activations Density 0.009%

    No Known Activations