© 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. 0-RES-JB
    11. 12266
    Prev
    Next
    INDEX
    Explanations

    What I see in the activations is that this neuron is looking for words related to sorrow or loss

    oai_token-act-pair · gpt-3.5-turbo

    words related to grief and bereavement

    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
    •layer 0 - sadness

    No Comments

    Negative Logits
    rolling
    -0.73
     Monkey
    -0.73
    Tyler
    -0.73
    ano
    -0.72
    oop
    -0.70
    Cool
    -0.69
     Contest
    -0.68
    Loop
    -0.68
     Rogue
    -0.68
    edited
    -0.67
    POSITIVE LOGITS
     bere
    3.30
     Bere
    1.82
     maternity
    1.67
     devoid
    1.51
     bes
    1.25
     Lerner
    1.12
     unthinkable
    1.08
     wedd
    1.07
     borne
    1.03
     Kers
    1.02
    Activations Density 0.052%

    No Known Activations