© 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. 0-RES-JB
    11. 22784
    Prev
    Next
    INDEX
    Explanations

    terms related to physical touch or emotional impact

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "touched."

    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
     Nielsen
    -0.66
     Pyr
    -0.65
    efficiency
    -0.63
     billing
    -0.62
     recruitment
    -0.61
     Coastal
    -0.60
     propaganda
    -0.59
     attrition
    -0.59
     slaughter
    -0.58
    spons
    -0.58
    POSITIVE LOGITS
     touched
    3.72
     touches
    2.10
     touching
    1.96
     touch
    1.95
     kissed
    1.54
    touch
    1.45
    Touch
    1.43
     impacted
    1.41
     interacted
    1.34
     Touch
    1.31
    Activations Density 0.014%

    No Known Activations