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. 5628
    Prev
    Next
    INDEX
    Explanations

    time-related terms, particularly focusing on comparisons between different time periods

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods and year-over-year comparisons

    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
    HCR
    -0.73
     carbohyd
    -0.69
    inite
    -0.66
    REDACTED
    -0.65
    mart
    -0.64
    CLASSIFIED
    -0.61
    FREE
    -0.60
    ITNESS
    -0.60
    HOU
    -0.58
    ESCO
    -0.58
    POSITIVE LOGITS
     Ago
    0.92
    frames
    0.90
     ago
    0.89
    ago
    0.83
     preceding
    0.82
    ibia
    0.80
     averages
    0.76
    frame
    0.74
    since
    0.74
    pan
    0.71
    Activations Density 0.186%

    No Known Activations