© 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. 0-RES-JB
    11. 2850
    Prev
    Next
    INDEX
    Explanations

    phrases related to electronic devices and technologies, particularly radios and batteries

    oai_token-act-pair · gpt-3.5-turbo

    references to radio and media outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vine
    -0.71
     Cedar
    -0.70
     spirit
    -0.68
     turnaround
    -0.66
     Roots
    -0.66
     deterrent
    -0.65
     scale
    -0.65
     stakes
    -0.64
     Joint
    -0.63
     lag
    -0.63
    POSITIVE LOGITS
    Radio
    3.08
    radio
    1.77
    Associated
    1.73
    Station
    1.39
    Center
    1.24
    Information
    1.17
    Gate
    1.15
    Weather
    1.10
    Slot
    1.10
    Poll
    1.09
    Activations Density 0.038%

    No Known Activations