© 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. 3-RES-JB
    11. 21285
    Prev
    Next
    INDEX
    Explanations

    references to specific technology terms, such as software updates and device names

    oai_token-act-pair · gpt-3.5-turbo

    references to tech products and updates related to software, particularly in relation to the "Jelly Bean" Android version and Microsoft Windows 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
     Prosecut
    -0.84
    uyomi
    -0.79
    eering
    -0.73
    atu
    -0.72
     Reverend
    -0.71
     Kills
    -0.71
     NAACP
    -0.71
     Suffolk
    -0.68
     Reconstruction
    -0.68
    apego
    -0.68
    POSITIVE LOGITS
     desktop
    1.02
     wearable
    0.89
     OLED
    0.88
     Nvidia
    0.88
     graphics
    0.87
     software
    0.87
     firmware
    0.87
     browsers
    0.86
     wireless
    0.86
     upgr
    0.86
    Activations Density 0.283%

    No Known Activations