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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-RES-JB
    6. 16606
    Prev
    Next
    INDEX
    Explanations

    instances of the word "until" followed by an action or condition

    oai_token-act-pair · gpt-3.5-turbo

    the word "until" and its various contexts in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pour
    -0.67
    ertain
    -0.65
     preserves
    -0.64
    Girl
    -0.63
    stick
    -0.60
    pl
    -0.60
    dragon
    -0.60
    cap
    -0.59
    hold
    -0.58
    LAB
    -0.58
    POSITIVE LOGITS
    terday
    0.77
     recently
    0.77
     hindsight
    0.74
     finally
    0.73
     realizing
    0.72
     discovering
    0.72
    xit
    0.71
    uitous
    0.68
     lately
    0.66
     suddenly
    0.66
    Activations Density 0.040%

    No Known Activations