© 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. 13571
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negation or contradiction

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating denial or contradiction of a previous statement

    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
    opez
    -0.77
    ngth
    -0.75
    ãĤ¨ãĥ«
    -0.71
    dies
    -0.69
    alties
    -0.68
    monds
    -0.64
     stripes
    -0.63
    pick
    -0.59
    assi
    -0.59
    anches
    -0.59
    POSITIVE LOGITS
     happening
    1.04
     happen
    0.89
     blat
    0.71
     Happ
    0.69
     occurring
    0.68
     unfolding
    0.66
     generational
    0.65
     ado
    0.64
    catentry
    0.63
     happens
    0.63
    Activations Density 0.266%

    No Known Activations