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. 7-RES-JB
    6. 15564
    Prev
    Next
    INDEX
    Explanations

    terms related to time, specifically references to particular periods

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods, specifically those prefixed with "mid-" indicating middle dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AVG
    -0.72
    edIn
    -0.70
     Ally
    -0.66
     Freed
    -0.66
     badges
    -0.66
     DRAG
    -0.65
     Ads
    -0.64
     Painter
    -0.64
     Starr
    -0.62
     Achievements
    -0.62
    POSITIVE LOGITS
    season
    1.20
    range
    1.18
    century
    1.18
    sized
    1.15
    term
    1.09
    sent
    1.09
    distance
    1.07
    ranking
    1.06
    grade
    1.06
    level
    1.05
    Activations Density 0.018%

    No Known Activations