© 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. 6-RES-JB
    11. 21955
    Prev
    Next
    INDEX
    Explanations

    The neuron is primarily looking for mentions of the internet

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Internet."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eters
    -0.85
    otte
    -0.85
    itol
    -0.78
    ursed
    -0.76
    geries
    -0.73
    lain
    -0.72
    avering
    -0.72
    ilts
    -0.72
    iffs
    -0.71
    lein
    -0.71
    POSITIVE LOGITS
     Explorer
    1.19
     Archive
    1.05
     Connection
    0.93
     Protocol
    0.90
     connectivity
    0.84
     Access
    0.83
     cafes
    0.83
     Crimes
    0.81
     Systems
    0.78
     cafe
    0.77
    Activations Density 0.018%

    No Known Activations