© 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. 8-RES-JB
    11. 7842
    Prev
    Next
    INDEX
    Explanations

    technical specifications such as storage capacity and RAM in electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    specifications and features related to computing devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mockery
    -0.81
     Situation
    -0.81
     volunt
    -0.79
     fallacy
    -0.76
     Cinderella
    -0.75
    orc
    -0.71
     folklore
    -0.70
     Trout
    -0.70
     Salvation
    -0.69
     Gould
    -0.68
    POSITIVE LOGITS
    Gb
    1.11
    MP
    1.07
    kHz
    1.05
    Hz
    1.03
    Mbps
    1.02
     PCIe
    1.00
    GB
    1.00
     watts
    0.99
     pixels
    0.98
    MHz
    0.97
    Activations Density 0.150%

    No Known Activations