© 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. 9-RES-JB
    11. 13858
    Prev
    Next
    INDEX
    Explanations

    phrases related to connections or relationships between two entities

    oai_token-act-pair · gpt-3.5-turbo

    references to pairs or relationships between entities

    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
    ogle
    -0.77
    umper
    -0.70
    mson
    -0.68
    undown
    -0.60
    adish
    -0.60
    mberg
    -0.59
    pletion
    -0.59
    ainment
    -0.58
    aroo
    -0.58
    kie
    -0.58
    POSITIVE LOGITS
     together
    2.01
     respectively
    1.91
    together
    1.80
     Together
    1.69
     jointly
    1.68
     alike
    1.66
     mutually
    1.63
     toget
    1.54
     interchange
    1.51
     combined
    1.37
    Activations Density 2.057%

    No Known Activations