© 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. 9759
    Prev
    Next
    INDEX
    Explanations

    technical terms related to security technologies and devices

    oai_token-act-pair · gpt-3.5-turbo

    technical terminology related to surveillance and monitoring systems

    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
    luster
    -0.70
    usterity
    -0.65
     adolesc
    -0.64
     berries
    -0.62
     rebell
    -0.61
     Rebell
    -0.61
     surpr
    -0.60
    urst
    -0.59
     roy
    -0.59
    cember
    -0.57
    POSITIVE LOGITS
     sensor
    0.74
     sensors
    0.74
    paio
    0.69
     detects
    0.69
     heater
    0.68
    devices
    0.68
     antennas
    0.68
     microphone
    0.67
     microphones
    0.67
     transmit
    0.67
    Activations Density 1.001%

    No Known Activations