Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 20750
    Prev
    Next
    INDEX
    Explanations

    actions involving movement or interaction between people in various settings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of actions involving people and movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ®é
    -0.70
     reliance
    -0.67
    awaru
    -0.66
     avoided
    -0.65
    phabet
    -0.63
    çīĪ
    -0.62
    ukong
    -0.61
    IVERS
    -0.61
     ratios
    -0.60
    inventoryQuantity
    -0.60
    POSITIVE LOGITS
     beside
    0.88
     overhead
    0.86
     menacing
    0.82
     threatening
    0.81
     unexpectedly
    0.80
     demanding
    0.77
     nearby
    0.77
     downstairs
    0.76
     beck
    0.75
     knocking
    0.75
    Activations Density 0.243%

    No Known Activations