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. 22188
    Prev
    Next
    INDEX
    Explanations

    mentions of past events

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "past" in various contexts

    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
    anguage
    -0.78
    shapeshifter
    -0.72
    Software
    -0.69
    Downloadha
    -0.68
    hyde
    -0.68
    tyard
    -0.67
    hz
    -0.66
    Reply
    -0.64
    zhen
    -0.64
    Dev
    -0.63
    POSITIVE LOGITS
    ebin
    1.44
    iche
    0.89
     tense
    0.88
    ures
    0.85
    imes
    0.74
     midnight
    0.73
    İ
    0.73
    ime
    0.73
     generations
    0.73
     week
    0.72
    Activations Density 0.024%

    No Known Activations