© 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. 13780
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparing or contrasting different items or concepts

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases indicating examples or references to other entities or events

    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
    ennes
    -0.81
    essing
    -0.78
    arbon
    -0.75
    ells
    -0.74
    atform
    -0.73
    elin
    -0.73
    inion
    -0.71
    enary
    -0.69
    inas
    -0.69
     enthusi
    -0.68
    POSITIVE LOGITS
    lihood
    1.32
    lier
    0.96
    liest
    0.92
     ours
    0.91
     hers
    0.77
     yours
    0.75
    minded
    0.67
    åĭ
    0.66
     theirs
    0.65
    pick
    0.65
    Activations Density 0.070%

    No Known Activations