© 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. 8-RES-JB
    11. 2449
    Prev
    Next
    INDEX
    Explanations

    words related to temperature or emotional control

    oai_token-act-pair · gpt-3.5-turbo

    references to temperature and temperament

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HHS
    -0.63
     Worlds
    -0.62
     Organizations
    -0.62
     Campus
    -0.60
     Defenders
    -0.59
    ded
    -0.59
     VID
    -0.59
    FF
    -0.58
    imity
    -0.57
     Hitman
    -0.57
    POSITIVE LOGITS
    amental
    1.32
     tant
    1.16
    mental
    1.14
    aments
    1.09
    ate
    1.03
    atures
    0.91
    ently
    0.87
    ance
    0.87
    ately
    0.87
    orously
    0.85
    Activations Density 0.071%

    No Known Activations