© 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. 4-RES-JB
    11. 853
    Prev
    Next
    INDEX
    Explanations

    So this neuron primarily looks for words related to influential people or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to influential individuals, organizations, or factors

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

    No Comments

    Negative Logits
    thia
    -0.78
    gged
    -0.76
    È
    -0.70
    few
    -0.70
     Homeless
    -0.69
    ©¶æ
    -0.69
    ciation
    -0.68
    á
    -0.68
    cedented
    -0.67
    ft
    -0.67
    POSITIVE LOGITS
     influ
    0.99
     influential
    0.96
     influence
    0.86
     endorsements
    0.83
     figures
    0.80
     role
    0.80
     personalities
    0.79
     gossip
    0.75
     influences
    0.73
     piece
    0.73
    Activations Density 0.013%

    No Known Activations