© 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. 6-RES-JB
    11. 16885
    Prev
    Next
    INDEX
    Explanations

    phrases where negation is involved

    oai_token-act-pair · gpt-3.5-turbo

    negative contractions suggesting inability or negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    catentry
    -0.81
    Offline
    -0.78
    ewater
    -0.72
    å
    -0.70
    orst
    -0.69
    iosyncr
    -0.68
    ãĥ¼ãĥĨãĤ£
    -0.67
    çĶ°
    -0.64
    ocr
    -0.64
     Ãľ
    -0.63
    POSITIVE LOGITS
     temptation
    0.77
     anymore
    0.64
     sight
    0.61
    amaz
    0.61
    FN
    0.58
     sweets
    0.57
     Bronx
    0.56
     grinning
    0.56
    INS
    0.56
    RAG
    0.56
    Activations Density 0.522%

    No Known Activations