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. 15792
    Prev
    Next
    INDEX
    Explanations

    phrases related to hindsight or looking back on past events

    oai_token-act-pair · gpt-3.5-turbo

    phrases and concepts related to reflection and reconsideration of past events

    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
    unin
    -0.68
    yan
    -0.65
     MIL
    -0.60
     kindred
    -0.59
     prisoner
    -0.58
    erto
    -0.58
    aves
    -0.58
    liam
    -0.57
    vy
    -0.57
    zzi
    -0.56
    POSITIVE LOGITS
     hindsight
    1.33
     retrospect
    1.20
     nostalg
    0.88
    é¾įå¥ij士
    0.88
    ibility
    0.81
    å§«
    0.81
    spection
    0.80
    spective
    0.78
     reflection
    0.78
    reflect
    0.75
    Activations Density 0.019%

    No Known Activations