© 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. 2568
    Prev
    Next
    INDEX
    Explanations

    terms related to computer programming and data structures, such as strings, objects, and keys

    oai_token-act-pair · gpt-3.5-turbo

    JSON format related to application metadata

    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
    ulty
    -0.79
    orno
    -0.73
    mma
    -0.70
    ewitness
    -0.69
    omorphic
    -0.68
    ween
    -0.67
    estones
    -0.66
    rien
    -0.65
    ogly
    -0.65
    emouth
    -0.65
    POSITIVE LOGITS
     {"
    1.14
    null
    1.12
     null
    1.08
     NULL
    0.97
     None
    0.93
    true
    0.90
     false
    0.89
     nil
    0.86
     undefined
    0.85
     ""
    0.85
    Activations Density 0.051%

    No Known Activations