© 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. 10488
    Prev
    Next
    INDEX
    Explanations

    references to emotional states, particularly mood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to emotions or feelings, especially focusing on the concept of mood

    oai_token-act-pair · gpt-3.5-turbo
    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
     WATCHED
    -0.74
    adr
    -0.73
     Universities
    -0.73
    ACTED
    -0.72
    Lay
    -0.69
     McKay
    -0.67
    chnology
    -0.67
    Ô
    -0.66
     Prosecut
    -0.65
    pta
    -0.65
    POSITIVE LOGITS
     mood
    1.08
     Mood
    0.85
     contag
    0.84
     swings
    0.76
    iness
    0.75
    y
    0.75
     conducive
    0.74
     stabil
    0.74
     disorder
    0.72
    atically
    0.72
    Activations Density 0.011%

    No Known Activations