© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 8407
    Prev
    Next
    INDEX
    Explanations

    information related to financial figures or amounts, specifically indicating an annual recurrence

    oai_token-act-pair · gpt-3.5-turbo

    references to annual or yearly occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     messed
    -0.66
     blink
    -0.60
     chat
    -0.60
    stration
    -0.59
     voic
    -0.59
    xd
    -0.59
     Silence
    -0.59
    text
    -0.58
     Anger
    -0.58
     feeling
    -0.56
    POSITIVE LOGITS
     annually
    3.39
     yearly
    2.29
     annual
    1.93
     quarterly
    1.52
     periodically
    1.42
     monthly
    1.42
     Annual
    1.41
    ennial
    1.29
     regularly
    1.25
    iann
    1.15
    Activations Density 0.013%

    No Known Activations