© 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. 7334
    Prev
    Next
    INDEX
    Explanations

    words related to mental health and personal development

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific concepts or entities related to “Mind” and locations associated with it

    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
    EStreamFrame
    -0.81
    usercontent
    -0.74
     Sight
    -0.68
    Dir
    -0.68
    inals
    -0.67
    ozo
    -0.66
    enegger
    -0.65
    filename
    -0.64
     Pigs
    -0.64
    resses
    -0.63
    POSITIVE LOGITS
     pedals
    0.67
    ashtra
    0.65
    terness
    0.65
    oland
    0.64
     steered
    0.64
    Ŀ
    0.63
     filibuster
    0.61
    hematically
    0.61
     Remastered
    0.61
    theless
    0.60
    Activations Density 0.190%

    No Known Activations