© 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. 20304
    Prev
    Next
    INDEX
    Explanations

    terms related to computer simulations and automated processes

    oai_token-act-pair · gpt-3.5-turbo

    references to simulations in various contexts

    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
    umper
    -0.79
    çĦ
    -0.78
    asha
    -0.76
    enny
    -0.76
    stones
    -0.72
    turn
    -0.72
    upon
    -0.69
    ymph
    -0.69
    imb
    -0.67
    ield
    -0.67
    POSITIVE LOGITS
     simulation
    1.21
     simulations
    1.21
     simulate
    1.09
     Simulation
    1.04
    ãĤ¼ãĤ¦ãĤ¹
    1.01
     simulated
    0.91
     simulator
    0.89
    eers
    0.84
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.83
     Simulator
    0.83
    Activations Density 0.014%

    No Known Activations