© 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. 6363
    Prev
    Next
    INDEX
    Explanations

    terms related to small things or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to "small" entities or concepts, particularly in relation to economics or business

    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
     largeDownload
    -0.72
    reon
    -0.70
     Rousse
    -0.69
    ILLE
    -0.65
    undrum
    -0.65
    afia
    -0.64
    VERTISEMENT
    -0.64
    ophen
    -0.64
     Michaels
    -0.62
    STAT
    -0.62
    POSITIVE LOGITS
    pox
    1.23
     increments
    0.96
     intestine
    0.93
    folk
    0.89
     batches
    0.89
    scale
    0.87
    holders
    0.86
     sized
    0.86
     fry
    0.83
     businesses
    0.81
    Activations Density 0.055%

    No Known Activations