© 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. 8-RES-JB
    11. 17232
    Prev
    Next
    INDEX
    Explanations

    terms related to division or disagreement in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "divided" or related concepts of division or separation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leeve
    -0.77
    ITNESS
    -0.75
    oken
    -0.72
    leigh
    -0.70
    ORTS
    -0.69
    CLA
    -0.68
    Notes
    -0.67
    trak
    -0.67
    elin
    -0.66
    ensitivity
    -0.65
    POSITIVE LOGITS
     hairs
    0.92
    naire
    0.83
     between
    0.83
    oslav
    0.82
     evenly
    0.81
    iple
    0.81
     divided
    0.79
     apart
    0.75
     amongst
    0.74
     unequ
    0.72
    Activations Density 0.039%

    No Known Activations