Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 24180
    Prev
    Next
    INDEX
    Explanations

    words related to antennas and related technical details

    oai_token-act-pair · gpt-3.5-turbo

    terms related to antennas and their characteristics

    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
    neys
    -0.93
     Jenner
    -0.77
    ween
    -0.76
    bart
    -0.70
    20439
    -0.70
    ney
    -0.69
    é»Ĵ
    -0.68
    soDeliveryDate
    -0.67
    dan
    -0.67
    clamation
    -0.67
    POSITIVE LOGITS
     antennas
    1.11
    eering
    1.10
     antenna
    1.01
    eers
    0.83
    daq
    0.82
     lobe
    0.80
     wire
    0.76
     wires
    0.76
     helic
    0.75
     poles
    0.74
    Activations Density 0.029%

    No Known Activations