© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 412
    Prev
    Next
    INDEX
    Explanations

    phrases related to thermal energy and radiation

    oai_token-act-pair · gpt-3.5-turbo

    references to thermal energy and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ando
    -0.74
    married
    -0.72
    mons
    -0.70
    onge
    -0.70
    èĢħ
    -0.69
    Dou
    -0.68
    endale
    -0.68
    voc
    -0.67
     Kou
    -0.66
     Fighters
    -0.65
    POSITIVE LOGITS
     thermal
    3.72
     Thermal
    2.92
     therm
    2.12
    Ther
    1.58
     temperature
    1.44
     heat
    1.43
     cooling
    1.43
     heating
    1.39
     infrared
    1.32
    Temperature
    1.29
    Activations Density 0.020%

    No Known Activations