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. 4378
    Prev
    Next
    INDEX
    Explanations

    phrases indicating future intentions or plans

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing future actions or expectations

    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
     vows
    -0.83
     watches
    -0.76
     bets
    -0.74
     lucky
    -0.73
     planning
    -0.72
     Learning
    -0.71
     visions
    -0.70
     Warning
    -0.69
     Pledge
    -0.69
     Checking
    -0.67
    POSITIVE LOGITS
     occur
    0.99
     encompass
    0.95
     resonate
    0.94
     diminish
    0.92
     dissolve
    0.89
     become
    0.89
     be
    0.88
     overshadow
    0.87
     dissip
    0.87
     signify
    0.86
    Activations Density 0.333%

    No Known Activations