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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 3192
    Prev
    Next
    INDEX
    Explanations

    mentions of wolves

    oai_token-act-pair · gpt-3.5-turbo

    references to wolves

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angan
    -0.76
    NAS
    -0.73
    arters
    -0.72
    eways
    -0.71
    claimed
    -0.71
    ursed
    -0.71
    arta
    -0.70
    office
    -0.70
    ritic
    -0.69
    unal
    -0.68
    POSITIVE LOGITS
     wolves
    1.41
     wolf
    1.19
    wolves
    1.11
     Wolves
    1.07
     Fenrir
    1.01
    wolf
    0.95
    hound
    0.94
    gang
    0.93
     Wolf
    0.90
    enstein
    0.90
    Activations Density 0.010%

    No Known Activations