© 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. 2-RES-JB
    11. 17550
    Prev
    Next
    INDEX
    Explanations

    instances of the word "contribution"

    oai_token-act-pair · gpt-3.5-turbo

    references to contributions

    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
     Rapt
    -0.64
    Sensor
    -0.63
     Lumpur
    -0.62
    Ther
    -0.62
    Ħ¢
    -0.62
    atters
    -0.61
    spect
    -0.61
    isen
    -0.61
    Correct
    -0.60
    tight
    -0.59
    POSITIVE LOGITS
     contributions
    0.98
     contribution
    0.98
     Contributions
    0.88
    iosyncr
    0.88
     contribute
    0.87
    umed
    0.83
    ertodd
    0.82
    jri
    0.81
    regor
    0.80
    ATURE
    0.79
    Activations Density 0.012%

    No Known Activations