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. 3292
    Prev
    Next
    INDEX
    Explanations

    the word "that" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "the fact that."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    QB
    -0.70
    aukee
    -0.66
    ron
    -0.65
    eal
    -0.63
    Guard
    -0.63
    WS
    -0.61
    ITCH
    -0.60
    MSN
    -0.60
    rup
    -0.60
    Y
    -0.59
    POSITIVE LOGITS
     they
    0.84
     nobody
    0.72
     pesky
    0.71
    */(
    0.70
     someone
    0.67
    soever
    0.66
     we
    0.66
     accompanies
    0.65
     THEY
    0.64
     he
    0.64
    Activations Density 0.089%

    No Known Activations