© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 6870
    Prev
    Next
    INDEX
    Explanations

    dimensions specified using numerical values, often relating to display screens

    oai_token-act-pair · gpt-3.5-turbo

    terms related to screen resolutions and dimensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zin
    -0.72
    aida
    -0.69
    irds
    -0.67
    agara
    -0.67
     fare
    -0.66
     rab
    -0.65
    uned
    -0.65
    ogy
    -0.64
    birds
    -0.64
    jay
    -0.64
    POSITIVE LOGITS
     768
    0.92
     1050
    0.91
     1440
    0.91
     1800
    0.89
     1200
    0.88
     1600
    0.87
     2048
    0.86
    1080
    0.86
     960
    0.86
    1800
    0.86
    Activations Density 0.070%

    No Known Activations