© 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. 8-RES-JB
    6. 7852
    Prev
    Next
    INDEX
    Explanations

    time-related phrases indicating a countdown or deadline

    oai_token-act-pair · gpt-3.5-turbo

    references to remaining time or deadlines

    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
     Cosponsors
    -0.88
    nik
    -0.75
    cult
    -0.72
    step
    -0.65
    ãĥĥãĥī
    -0.61
    pmwiki
    -0.60
     bir
    -0.59
    wcsstore
    -0.58
    pecially
    -0.57
     visitor
    -0.56
    POSITIVE LOGITS
    akia
    0.73
     allotted
    0.72
     unanswered
    0.71
    eem
    0.71
    },"
    0.69
    =~
    0.69
    atile
    0.68
     reserves
    0.66
     unexpl
    0.65
     unresolved
    0.65
    Activations Density 0.083%

    No Known Activations