© 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. 1-RES-JB
    6. 21085
    Prev
    Next
    INDEX
    Explanations

    references to a specific type of person - a neighbor

    oai_token-act-pair · gpt-3.5-turbo

    references to neighbors in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ename
    -0.85
    oola
    -0.78
    uchin
    -0.78
    ormonal
    -0.76
    inen
    -0.73
    allery
    -0.73
    aver
    -0.72
    isting
    -0.72
    argon
    -0.71
    oric
    -0.71
    POSITIVE LOGITS
     neighbor
    1.56
     neighbors
    1.43
     neighbour
    1.29
     Neigh
    1.22
     neighbours
    1.15
     Neighbor
    1.13
    Neigh
    0.96
     Neighborhood
    0.94
    liness
    0.85
     neighb
    0.83
    Activations Density 0.007%

    No Known Activations