© 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. 2-RES-JB
    11. 9097
    Prev
    Next
    INDEX
    Explanations

    mentions of temperature or situations where a certain level of boldness or audacity is displayed

    oai_token-act-pair · gpt-3.5-turbo

    mentions of temperature and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heid
    -0.76
     Palmer
    -0.74
     Goods
    -0.73
     Pyramid
    -0.73
    lihood
    -0.72
     Away
    -0.71
     Hutch
    -0.70
     Wick
    -0.70
     Parties
    -0.70
     Ago
    -0.70
    POSITIVE LOGITS
     tem
    1.28
    ason
    0.95
    ented
    0.95
    unci
    0.91
    pos
    0.89
    pers
    0.88
    ps
    0.85
    erity
    0.83
    agogue
    0.80
    otype
    0.78
    Activations Density 0.004%

    No Known Activations