© 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. 11-RES-JB
    11. 22364
    Prev
    Next
    INDEX
    Explanations

    phrases related to communications or exchanges between individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "over."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ittal
    -0.77
     holder
    -0.67
    eria
    -0.66
    OY
    -0.66
    YS
    -0.62
    ELY
    -0.61
    OL
    -0.61
    ORY
    -0.60
    osure
    -0.59
     quo
    -0.58
    POSITIVE LOGITS
    lord
    1.00
     lunch
    0.99
     dinner
    0.97
    joy
    0.94
    priced
    0.92
     Thanksgiving
    0.89
     drinks
    0.89
     breakfast
    0.88
    comes
    0.88
    reaching
    0.88
    Activations Density 0.061%

    No Known Activations