© 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. 18687
    Prev
    Next
    INDEX
    Explanations

    references to being in a state of extreme need or craving

    oai_token-act-pair · gpt-3.5-turbo

    the word "hung" in various contexts

    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
    姫
    -0.71
    ISO
    -0.68
    ignty
    -0.67
     Dee
    -0.64
    caps
    -0.64
    pace
    -0.63
    м
    -0.63
    ãĥĸ
    -0.62
    ãĥ¯
    -0.62
    owell
    -0.61
    POSITIVE LOGITS
    rily
    0.98
    river
    0.85
    Hung
    0.84
    ary
    0.81
    ry
    0.80
     Banner
    0.78
    yrinth
    0.75
    arian
    0.75
    dad
    0.75
    umph
    0.73
    Activations Density 0.006%

    No Known Activations