© 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. 4-RES-JB
    11. 15239
    Prev
    Next
    INDEX
    Explanations

    Latin words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    words and terms related to biological classifications and nomenclature

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

    No Comments

    Negative Logits
    ricks
    -0.70
    kowski
    -0.69
     scraps
    -0.69
     lobb
    -0.68
     livelihood
    -0.67
     Wak
    -0.65
    INGTON
    -0.63
     Jinn
    -0.63
    rish
    -0.63
     surn
    -0.62
    POSITIVE LOGITS
    ptions
    0.94
     tion
    0.86
    uries
    0.81
    hement
    0.80
    arial
    0.79
    poral
    0.79
    ples
    0.79
    aurus
    0.78
    ensis
    0.78
    autical
    0.77
    Activations Density 0.102%

    No Known Activations