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. 3561
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparing past and present states

    oai_token-act-pair · gpt-3.5-turbo

    comparisons focused on changes over time

    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
    pract
    -0.73
    locks
    -0.72
    Dialogue
    -0.71
    ility
    -0.70
    Zen
    -0.69
     Latter
    -0.63
    552
    -0.63
    $$$$
    -0.62
    weekly
    -0.62
    rub
    -0.62
    POSITIVE LOGITS
     previous
    1.02
     earlier
    1.01
     predecessors
    0.93
     inception
    0.92
     predecessor
    0.92
     previously
    0.90
     preceding
    0.73
     lows
    0.73
     originally
    0.73
     original
    0.72
    Activations Density 0.892%

    No Known Activations