© 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. 8-RES-JB
    11. 16935
    Prev
    Next
    INDEX
    Explanations

    words related to internet and coding

    oai_token-act-pair · gpt-3.5-turbo

    specific technical terms and vocabulary related to various contexts such as technology, literature, and medicine

    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
    units
    -0.92
    models
    -0.90
    sites
    -0.87
     Cups
    -0.87
    Vert
    -0.84
    anders
    -0.83
    features
    -0.82
     trails
    -0.81
    modules
    -0.80
    artifacts
    -0.80
    POSITIVE LOGITS
     standpoint
    0.97
    achable
    0.76
     version
    0.76
    iece
    0.75
     foothold
    0.74
    illary
    0.73
    iary
    0.70
     copy
    0.70
     perspective
    0.70
     acquaintance
    0.69
    Activations Density 0.321%

    No Known Activations