© 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. 1-RES-JB
    11. 7984
    Prev
    Next
    INDEX
    Explanations

    references to physical heat or temperature

    oai_token-act-pair · gpt-3.5-turbo

    references to heat and temperature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VICE
    -0.84
    MSN
    -0.70
     Columbia
    -0.68
    ibia
    -0.65
    vous
    -0.64
    805
    -0.63
    MENT
    -0.62
    minster
    -0.62
     Suc
    -0.61
     Crossref
    -0.61
    POSITIVE LOGITS
     heat
    1.20
    heat
    1.08
     oven
    1.05
     heats
    1.04
    Heat
    1.01
     hotter
    0.96
    waves
    0.95
     heating
    0.92
     temperatures
    0.90
    bender
    0.90
    Activations Density 0.014%

    No Known Activations