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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 22786
    Prev
    Next
    INDEX
    Explanations

    events or actions that happen at a specific point in time, particularly events that occur later in time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the passage of time or events that happened later

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esville
    -0.68
    tnc
    -0.66
    yip
    -0.60
    Els
    -0.59
    VALUE
    -0.59
     juices
    -0.58
    anooga
    -0.58
    Desktop
    -0.57
    emo
    -0.57
    =~=~
    -0.56
    POSITIVE LOGITS
     than
    0.87
    ,
    0.83
    !,
    0.74
     when
    0.74
    .,
    0.66
    !
    0.65
     succumbed
    0.64
    ,[
    0.63
     onwards
    0.63
     –
    0.62
    Activations Density 0.068%

    No Known Activations