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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 4890
    Prev
    Next
    INDEX
    Explanations

    the concept of "execution" with a strong focus on actions, tasks, and plans

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word 'execution' and its various forms

    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
    ijn
    -0.77
     Tire
    -0.68
    este
    -0.66
    iers
    -0.66
     Greater
    -0.64
     Alto
    -0.63
    deb
    -0.62
    bie
    -0.62
     Soda
    -0.60
    anton
    -0.59
    POSITIVE LOGITS
     execute
    0.94
     executes
    0.90
     executing
    0.86
    sequence
    0.83
    eering
    0.83
     execution
    0.83
     executions
    0.80
    uate
    0.77
    isites
    0.76
    eers
    0.76
    Activations Density 0.016%

    No Known Activations