© 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. 18538
    Prev
    Next
    INDEX
    Explanations

    terms related to temperature

    oai_token-act-pair · gpt-3.5-turbo

    terms related to temperature

    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
     Palmer
    -0.75
    ION
    -0.73
    heid
    -0.73
     Drugs
    -0.72
     Universities
    -0.71
     Parties
    -0.70
     Bild
    -0.69
     Dawkins
    -0.68
     Spending
    -0.68
     Scotia
    -0.68
    POSITIVE LOGITS
    porary
    1.21
    tem
    1.10
    perature
    1.06
    perate
    1.03
     tem
    1.02
    achine
    0.99
    pos
    0.96
    arily
    0.94
    erity
    0.93
    plates
    0.91
    Activations Density 0.006%

    No Known Activations