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. 15174
    Prev
    Next
    INDEX
    Explanations

    phrases related to investigations and legal matters

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "In" followed by a numerical value or a significant time reference

    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
     spoil
    -0.70
     looms
    -0.67
    reon
    -0.64
    76561
    -0.63
    channelAvailability
    -0.63
     lov
    -0.60
     unlocks
    -0.59
    :/
    -0.59
     pim
    -0.58
     litter
    -0.57
    POSITIVE LOGITS
     addition
    1.28
    juries
    1.21
    ventory
    1.21
    herent
    1.19
    flation
    1.19
     spite
    1.17
    cluding
    1.15
    jured
    1.14
     contrast
    1.13
    clusion
    1.13
    Activations Density 0.165%

    No Known Activations