© 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. 2-RES-JB
    11. 8172
    Prev
    Next
    INDEX
    Explanations

    words related to heating and energy systems

    oai_token-act-pair · gpt-3.5-turbo
    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
    print
    -0.71
    ogo
    -0.68
    onel
    -0.64
    say
    -0.63
    clusions
    -0.61
     McCull
    -0.61
    go
    -0.60
    inals
    -0.60
    âĢ¢âĢ¢
    -0.59
    uterte
    -0.59
    POSITIVE LOGITS
     heating
    1.18
     oven
    1.05
     heater
    1.00
     insulation
    0.93
     furnace
    0.90
     appliances
    0.85
    ther
    0.84
     stove
    0.83
     hotter
    0.82
     therm
    0.80
    Activations Density 0.008%

    No Known Activations