© 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. 2-RES-JB
    11. 17649
    Prev
    Next
    INDEX
    Explanations

    phrases related to electrical sockets and items that can be attached to the body

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sockets and socket connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Whitman
    -0.73
    sweet
    -0.65
     Ames
    -0.65
    GGGG
    -0.63
     Huffington
    -0.63
    dit
    -0.62
    GM
    -0.60
     Lean
    -0.60
    birth
    -0.60
     Narc
    -0.60
    POSITIVE LOGITS
     socket
    1.40
     sockets
    1.34
    socket
    1.27
     Socket
    1.13
    ocket
    0.84
    Socket
    0.84
     wrench
    0.83
    ockets
    0.82
    chio
    0.80
    heed
    0.80
    Activations Density 0.010%

    No Known Activations