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. 5-RES-JB
    6. 8621
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Rog" with varying degrees of similarity, possibly indicating a focus on detecting specific names or terms related to "Rog."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Rog" 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 @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spaced
    -0.74
     Tribal
    -0.73
    pora
    -0.72
    ãĥĩãĤ£
    -0.67
    ãĥ¯ãĥ³
    -0.67
    birth
    -0.67
     kHz
    -0.66
     spores
    -0.65
     []
    -0.64
    BIP
    -0.62
    POSITIVE LOGITS
    ues
    1.37
    uel
    1.24
    uish
    1.24
    uers
    1.08
    ued
    1.06
    UE
    1.03
    atis
    0.93
    uing
    0.91
    adier
    0.91
     Rog
    0.90
    Activations Density 0.008%

    No Known Activations