© 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. 4-RES-JB
    11. 17067
    Prev
    Next
    INDEX
    Explanations

    phrases related to electrical sockets

    oai_token-act-pair · gpt-3.5-turbo

    terms related to computer hardware, specifically socket configurations and connectivity

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

    No Comments

    Negative Logits
     Whitman
    -0.71
    birth
    -0.67
    hig
    -0.64
     Ames
    -0.63
     Huffington
    -0.62
     Hum
    -0.62
    ORGE
    -0.59
    ATHER
    -0.59
    GGGG
    -0.59
    ãģĤ
    -0.59
    POSITIVE LOGITS
     socket
    1.19
     sockets
    1.12
    socket
    1.06
     Socket
    1.02
    rings
    0.86
     wrench
    0.82
    ocket
    0.81
    chio
    0.80
    omial
    0.77
    uitous
    0.76
    Activations Density 0.014%

    No Known Activations