© 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. 10000
    Prev
    Next
    INDEX
    Explanations

    phrases related to someone returning home or coming home from different places

    oai_token-act-pair · gpt-3.5-turbo

    instances of returning home or transitions related to homecoming

    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
    oppable
    -0.74
     punishable
    -0.73
    faces
    -0.71
     persists
    -0.68
    iste
    -0.68
     therein
    -0.67
    eries
    -0.66
     thereof
    -0.65
    aspx
    -0.64
    itutional
    -0.64
    POSITIVE LOGITS
     lunch
    1.15
     dinner
    1.12
     breakfast
    1.08
     brunch
    1.07
     vacation
    1.06
     birthday
    1.06
     holidays
    1.06
     Thanksgiving
    1.02
     holiday
    1.01
     midday
    0.99
    Activations Density 0.389%

    No Known Activations