© 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. 1-RES-JB
    11. 16189
    Prev
    Next
    INDEX
    Explanations

    instances where something is done repeatedly or as a regular practice

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "routinely" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lad
    -0.77
    soc
    -0.72
    nah
    -0.68
     Shining
    -0.67
     Emir
    -0.66
    istan
    -0.65
     Syri
    -0.65
     Millennium
    -0.65
     Straw
    -0.64
    gar
    -0.64
    POSITIVE LOGITS
    theless
    0.97
     pract
    0.94
     routinely
    0.91
    entimes
    0.86
     encountered
    0.86
    ãĤ©
    0.79
     employed
    0.79
     encount
    0.78
    ©¶æ
    0.78
     complained
    0.77
    Activations Density 0.006%

    No Known Activations