© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 3137
    Prev
    Next
    INDEX
    Explanations

    the prefix "un-" followed by an adjective

    oai_token-act-pair · gpt-3.5-turbo

    words prefixed with "un" that imply negation or contradiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Madness
    -0.74
     basement
    -0.72
     gorilla
    -0.66
     Tile
    -0.66
     Clause
    -0.65
     Patriarch
    -0.65
     Garden
    -0.65
     Mata
    -0.65
     Alma
    -0.64
     Kry
    -0.62
    POSITIVE LOGITS
    athom
    1.55
    riend
    1.53
    ortunately
    1.49
    ortun
    1.43
    avour
    1.38
    requently
    1.30
    ortunate
    1.27
    requ
    1.25
    requent
    1.24
    amiliar
    1.22
    Activations Density 0.025%

    No Known Activations