© 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. 3-RES-JB
    11. 6917
    Prev
    Next
    INDEX
    Explanations

    notable or remarkable items or details

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "notably" indicating significant points or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.86
    rieving
    -0.78
    uel
    -0.75
    ravel
    -0.74
    iche
    -0.72
    elf
    -0.71
    lyn
    -0.71
    imeter
    -0.71
    aily
    -0.70
    rive
    -0.68
    POSITIVE LOGITS
     absent
    0.90
     lacking
    0.74
    ãĤ´ãĥ³
    0.71
     spared
    0.70
     Remastered
    0.69
     Included
    0.68
     distingu
    0.67
    shown
    0.66
    æ³
    0.66
     endowed
    0.66
    Activations Density 0.013%

    No Known Activations