© 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. 1880
    Prev
    Next
    INDEX
    Explanations

    references to research methodology

    oai_token-act-pair · gpt-3.5-turbo

    mentions of research methodology

    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
    igi
    -0.68
    ership
    -0.65
    ergy
    -0.64
     nurs
    -0.63
    engers
    -0.63
    oÄŁ
    -0.62
    green
    -0.58
    worth
    -0.57
    mington
    -0.57
    ginx
    -0.57
    POSITIVE LOGITS
     methodology
    0.98
    ologies
    0.98
    OLOGY
    0.96
     Method
    0.94
    utics
    0.91
    ology
    0.89
    olicy
    0.87
    Method
    0.84
    krit
    0.82
    METHOD
    0.81
    Activations Density 0.010%

    No Known Activations