© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14794
    Prev
    Next
    INDEX
    Explanations

    words related to wireless technology or wireless communication

    oai_token-act-pair · gpt-3.5-turbo

    references to wireless technology and related topics

    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
    udo
    -0.89
    ablishment
    -0.82
    orian
    -0.81
    itia
    -0.80
    auder
    -0.80
    ivia
    -0.79
     Rite
    -0.79
     Petr
    -0.78
    sei
    -0.76
    oldemort
    -0.76
    POSITIVE LOGITS
     broadband
    0.94
     connectivity
    0.92
     networking
    0.92
    phone
    0.91
     wireless
    0.88
     routers
    0.86
     carriers
    0.86
     imaging
    0.86
     devices
    0.85
     headsets
    0.85
    Activations Density 0.010%

    No Known Activations