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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 9170
    Prev
    Next
    INDEX
    Explanations

    features or characteristics described about various technological devices

    oai_token-act-pair · gpt-3.5-turbo

    references to features and specifications of electronic devices

    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
    jah
    -0.78
    iffe
    -0.74
    prison
    -0.73
    ertain
    -0.72
    rn
    -0.71
    example
    -0.70
    Companies
    -0.70
    icult
    -0.70
    founded
    -0.69
    =#
    -0.69
    POSITIVE LOGITS
     upgraded
    1.11
     adjustable
    1.02
     Bluetooth
    1.00
     upgrades
    0.97
     removable
    0.96
     enhanced
    0.93
     touchscreen
    0.93
     HDMI
    0.92
     specs
    0.92
     AES
    0.91
    Activations Density 0.213%

    No Known Activations