© 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 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. 2-RES-JB
    11. 16090
    Prev
    Next
    INDEX
    Explanations

    phrases related to network and computer systems

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "AD" followed by numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.97
    ãĤ¡
    -0.94
     Parenthood
    -0.75
    Ń·
    -0.69
    borough
    -0.68
    ãĥīãĥ©ãĤ´ãĥ³
    -0.67
     Sturgeon
    -0.67
     Kubrick
    -0.66
     htt
    -0.66
    ãĤ©
    -0.66
    POSITIVE LOGITS
    VERTISEMENT
    1.35
    vantage
    1.04
    venture
    0.95
    VERTIS
    0.95
    MIN
    0.90
    iamond
    0.88
    JECT
    0.87
    visor
    0.85
    DI
    0.84
    vance
    0.83
    Activations Density 0.007%

    No Known Activations