© 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. 1-RES-JB
    11. 22195
    Prev
    Next
    INDEX
    Explanations

    phrases containing negative emotions or criticism

    oai_token-act-pair · gpt-3.5-turbo

    instances of critical commentary or statements made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ccording
    -0.86
    otype
    -0.71
     Rescue
    -0.63
     srf
    -0.61
    rafted
    -0.61
    versely
    -0.59
    RH
    -0.59
    ces
    -0.59
    ope
    -0.59
     Recon
    -0.59
    POSITIVE LOGITS
     remarks
    1.26
     comments
    1.03
    æĥ
    0.81
     aloud
    0.76
     slurs
    0.75
    ault
    0.75
    ä¹ĭ
    0.73
    gow
    0.73
     aside
    0.73
     remark
    0.72
    Activations Density 0.014%

    No Known Activations