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. 11-RES-JB
    6. 8117
    Prev
    Next
    INDEX
    Explanations

    time-related information like dates

    oai_token-act-pair · gpt-3.5-turbo

    instances of time references indicating "last" followed by a time period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adle
    -0.74
    roots
    -0.67
    gans
    -0.65
    okers
    -0.64
    holes
    -0.63
    ongs
    -0.63
    hement
    -0.63
    acebook
    -0.60
    ARDS
    -0.58
    paio
    -0.58
    POSITIVE LOGITS
     month
    1.70
     week
    1.69
     year
    1.50
     summer
    1.40
     weekend
    1.39
     November
    1.34
     night
    1.33
     autumn
    1.33
     October
    1.33
     December
    1.32
    Activations Density 0.062%

    No Known Activations