© 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
    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. 10247
    Prev
    Next
    INDEX
    Explanations

    references to programs, particularly related to various topics such as writing, energy upgrades, rape victim care, biophysics, securities regulation, game development, and more

    oai_token-act-pair · gpt-3.5-turbo

    references to specific programs and initiatives

    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
     volcanic
    -0.65
     humble
    -0.64
    icas
    -0.64
    ween
    -0.63
     vap
    -0.63
     harbour
    -0.62
     Ves
    -0.62
     statues
    -0.62
     stake
    -0.61
    plets
    -0.61
    POSITIVE LOGITS
    mable
    1.38
    matically
    1.23
    matic
    1.09
    program
    1.02
     programs
    1.00
     program
    0.99
    Program
    0.93
     Gutenberg
    0.90
     Programs
    0.89
    mers
    0.82
    Activations Density 0.026%

    No Known Activations