© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 15306
    Prev
    Next
    INDEX
    Explanations

    references to specific time periods such as "earlier this week/month"

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the word "this" within the text

    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
     Izan
    -0.73
    76561
    -0.68
     Zy
    -0.63
    vu
    -0.61
    oros
    -0.61
    sers
    -0.59
    ilet
    -0.59
     Rated
    -0.58
    916
    -0.58
    bet
    -0.58
    POSITIVE LOGITS
     month
    1.31
     week
    1.26
     year
    1.12
     afternoon
    1.11
     morning
    1.04
     semester
    1.03
     evening
    1.00
     summer
    0.99
     decade
    0.95
     weekend
    0.95
    Activations Density 0.041%

    No Known Activations