© 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. 3387
    Prev
    Next
    INDEX
    Explanations

    differences or variations in characteristics, attributes, or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "differ" and its variations, indicating a focus on differences or distinctions between entities or concepts

    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
     accelerator
    -0.64
    åľ
    -0.61
     cavity
    -0.60
     Minotaur
    -0.58
    icum
    -0.58
    ãĥ©
    -0.57
     roller
    -0.57
     Pione
    -0.57
     opener
    -0.56
     Orange
    -0.56
    POSITIVE LOGITS
    rets
    0.94
    inance
    0.92
    iculty
    0.91
    erent
    0.82
    erences
    0.81
    rences
    0.80
    inion
    0.80
    inances
    0.80
    indal
    0.80
    reciation
    0.79
    Activations Density 0.017%

    No Known Activations