© 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. 22261
    Prev
    Next
    INDEX
    Explanations

    phrases where an individual is emphasizing or highlighting a point or concern

    oai_token-act-pair · gpt-3.5-turbo

    references to feelings of stress or anxiety

    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
    izons
    -0.89
    advertising
    -0.86
    ä½ľ
    -0.76
    Snow
    -0.72
    kay
    -0.69
    DragonMagazine
    -0.68
    Beck
    -0.67
    acqu
    -0.66
    eatured
    -0.66
    Guard
    -0.66
    POSITIVE LOGITS
    enegger
    0.84
     stressed
    0.82
    alam
    0.72
     conduc
    0.71
     stresses
    0.69
     stressing
    0.68
     urgency
    0.68
     horizont
    0.67
    ariat
    0.66
    enger
    0.66
    Activations Density 0.012%

    No Known Activations