© 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. 23599
    Prev
    Next
    INDEX
    Explanations

    references to the name "Jalen"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Jalen Ramsey

    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
     Nationwide
    -0.78
     Parenthood
    -0.76
    ãģį
    -0.76
     Dying
    -0.73
     Debor
    -0.72
    天
    -0.71
    ãĥĩãĤ£
    -0.71
     SUP
    -0.69
    士
    -0.69
     Columb
    -0.65
    POSITIVE LOGITS
    aji
    0.96
    amel
    0.95
     Jal
    0.93
    aya
    0.89
    ules
    0.89
    peg
    0.86
    ppo
    0.84
    oha
    0.82
    olla
    0.82
    iah
    0.82
    Activations Density 0.005%

    No Known Activations