© 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. 4-RES-JB
    11. 9264
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparison or similarity

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve the concept of "such as" for providing examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÃĥÃĤ
    -0.75
    formance
    -0.67
    ival
    -0.66
    icter
    -0.65
    folios
    -0.64
    erial
    -0.63
     exting
    -0.63
    ÃĥÃĤÃĥÃĤ
    -0.61
    chnology
    -0.61
    ictional
    -0.60
    POSITIVE LOGITS
    pired
    0.79
    lihood
    0.78
     ours
    0.77
    pins
    0.67
    otin
    0.66
    pire
    0.64
    apple
    0.61
    æĢ
    0.59
    åĭ
    0.59
    pick
    0.59
    Activations Density 0.041%

    No Known Activations