© 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. 7029
    Prev
    Next
    INDEX
    Explanations

    specific names or terms related to a person named "Suda"

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "tread" and variations of the word “Sud” related to territoriality

    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
    urate
    -0.81
    ylum
    -0.80
    nect
    -0.77
    UNCH
    -0.75
    uate
    -0.72
    starter
    -0.71
    adelphia
    -0.71
    ASE
    -0.71
    ument
    -0.70
    uries
    -0.70
    POSITIVE LOGITS
     tread
    1.05
    iosyncr
    0.81
     Horses
    0.79
    DIT
    0.77
    cliffe
    0.76
     Curiosity
    0.75
     pse
    0.74
    ding
    0.73
    mallow
    0.71
    Ö¼
    0.70
    Activations Density 0.025%

    No Known Activations