© 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. 10-RES-JB
    11. 10122
    Prev
    Next
    INDEX
    Explanations

    words related to communication technologies and methods

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with communication, particularly in contexts involving security and monitoring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    steen
    -0.89
    endon
    -0.84
    iless
    -0.84
    lein
    -0.83
    gling
    -0.82
    herty
    -0.78
    riks
    -0.76
    engeance
    -0.75
    ighed
    -0.73
    jury
    -0.73
    POSITIVE LOGITS
     channels
    1.15
     networks
    1.06
     channel
    0.95
     protocols
    0.93
     network
    0.91
     protocol
    0.89
     medium
    0.87
    communications
    0.85
     communications
    0.85
     interception
    0.83
    Activations Density 0.047%

    No Known Activations