© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 22343
    Prev
    Next
    INDEX
    Explanations

    names or units of measurement related to weight or energy, especially kilowatt-hour

    oai_token-act-pair · gpt-3.5-turbo

    terms related to measurements of energy (kilo, kilowatt, hectowatt)

    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
     Fargo
    -0.76
    Discussion
    -0.71
     Forbidden
    -0.71
     Romance
    -0.69
     Advice
    -0.67
    Virgin
    -0.65
     Akin
    -0.64
     Admir
    -0.64
     Flight
    -0.64
     Cause
    -0.63
    POSITIVE LOGITS
    oby
    1.19
    mos
    1.08
    oton
    1.03
    kil
    1.00
    imet
    0.99
    ogram
    0.93
    tern
    0.92
    imeters
    0.90
    ths
    0.90
    ted
    0.89
    Activations Density 0.007%

    No Known Activations