Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 8937
    Prev
    Next
    INDEX
    Explanations

    expressions related to reactions or emotional responses

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the word "when" in contexts indicating timing or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "when", "whenever", "if", "after"

    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.93
    arnaev
    -0.90
    illary
    -0.83
    ormal
    -0.74
    antage
    -0.74
    ictionary
    -0.73
    olars
    -0.73
    hazard
    -0.73
    Stew
    -0.72
    abal
    -0.71
    POSITIVE LOGITS
     startled
    0.86
    soever
    0.84
     witnessing
    0.75
     unsuccessful
    0.72
     uttered
    0.70
     recalling
    0.70
     bitten
    0.67
     hearing
    0.67
     passers
    0.65
     greeting
    0.64
    Activations Density 0.193%

    No Known Activations