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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 17745
    Prev
    Next
    INDEX
    Explanations

    temperature measurements in degrees Celsius or Fahrenheit

    oai_token-act-pair · gpt-3.5-turbo

    temperature readings in degrees Celsius and Fahrenheit

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Saga
    -0.83
    ulations
    -0.74
     purse
    -0.74
    etsk
    -0.72
    gotten
    -0.71
    abor
    -0.69
    plex
    -0.68
    ardless
    -0.68
    eson
    -0.67
     collectors
    -0.67
    POSITIVE LOGITS
    º
    1.15
    °
    1.11
    º
    1.01
     Celsius
    0.99
    elsius
    0.99
     Fahrenheit
    0.97
    ¿
    0.86
    ³
    0.83
    âĶĢâĶĢâĶĢâĶĢ
    0.81
    terness
    0.81
    Activations Density 0.009%

    No Known Activations