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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 16908
    Prev
    Next
    INDEX
    Explanations

    time-based expressions indicating a period before an event occurs

    oai_token-act-pair · gpt-3.5-turbo

    references to time intervals in the future

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Balance
    -0.62
    idth
    -0.59
    equality
    -0.59
    levision
    -0.59
     Cantor
    -0.58
     BaseType
    -0.58
    ãĤ¨ãĥ«
    -0.58
     Binding
    -0.57
     Dru
    -0.57
    ghazi
    -0.57
    POSITIVE LOGITS
     overdue
    1.12
     away
    1.03
     ahead
    0.98
     removed
    0.89
    fetched
    0.83
     Away
    0.83
     distant
    0.82
     ago
    0.78
     awa
    0.78
     gone
    0.78
    Activations Density 0.098%

    No Known Activations