© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9342
    Prev
    Next
    INDEX
    Explanations

    phrases related to competition or selection

    oai_token-act-pair · gpt-3.5-turbo

    the concept of prioritization or ranking

    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
    antry
    -0.79
    ento
    -0.77
    oulder
    -0.75
    ocl
    -0.67
    alion
    -0.65
     rapp
    -0.63
    nesota
    -0.62
    emed
    -0.62
     Aval
    -0.61
    erville
    -0.61
    POSITIVE LOGITS
    ©¶æ¥µ
    0.66
     blockade
    0.63
    ²¾
    0.63
     Areas
    0.60
     margins
    0.60
     ):
    0.59
    mma
    0.58
     Deng
    0.57
    cyclopedia
    0.57
     coffers
    0.57
    Activations Density 0.000%

    No Known Activations