© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 17958
    Prev
    Next
    INDEX
    Explanations

    technical commands related to computer programming or digital games

    oai_token-act-pair · gpt-3.5-turbo

    phrases that begin with "More" followed by additional information or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atan
    -0.70
     2024
    -0.69
    itudes
    -0.68
    keeping
    -0.67
    oresc
    -0.65
    ļé
    -0.65
    xtap
    -0.65
    DD
    -0.64
    RL
    -0.63
    RN
    -0.63
    POSITIVE LOGITS
     importantly
    1.12
     than
    1.11
     ado
    1.09
     Than
    1.07
     sophisticated
    0.85
    than
    0.82
     mature
    0.81
     interesting
    0.80
     Likely
    0.78
     important
    0.77
    Activations Density 0.104%

    No Known Activations