© 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. 10-RES-JB
    11. 24480
    Prev
    Next
    INDEX
    Explanations

    The neuron is primarily looking for words related to living and working together

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to coexistence and collaborative actions

    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
     Cosponsors
    -0.73
    Reader
    -0.68
     caut
    -0.66
    Reviewer
    -0.65
     Timbers
    -0.64
     Whedon
    -0.64
     Hacker
    -0.64
     Roof
    -0.64
     Trojan
    -0.64
    èĢħ
    -0.63
    POSITIVE LOGITS
     breathing
    1.04
    death
    1.02
     death
    0.99
     dying
    0.98
     breathe
    0.98
     limb
    0.93
     breat
    0.92
     breathed
    0.90
     dies
    0.87
     livelihood
    0.84
    Activations Density 0.124%

    No Known Activations