© 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. 9-RES-JB
    11. 7551
    Prev
    Next
    INDEX
    Explanations

    keywords related to radio communications and frequencies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of radio and related frequency terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Snape
    -0.78
    ortium
    -0.78
    rir
    -0.76
    lihood
    -0.73
     Jol
    -0.72
    laus
    -0.70
     Goods
    -0.69
     Virtue
    -0.69
    oldemort
    -0.67
     Staples
    -0.67
    POSITIVE LOGITS
    activity
    1.13
    active
    1.11
    actively
    1.10
    frequency
    1.08
     stations
    1.02
     broadcasts
    1.00
     station
    0.97
     broadcasters
    0.93
     transmitter
    0.91
     silence
    0.91
    Activations Density 0.032%

    No Known Activations