Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-RES-JB
    6. 22045
    Prev
    Next
    INDEX
    Explanations

    information related to routines or events happening on a yearly basis

    oai_token-act-pair · gpt-3.5-turbo

    the term "annually" and its related context of yearly statistics or events

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

    No Comments

    Negative Logits
    holes
    -0.82
    ery
    -0.75
    bern
    -0.68
    ster
    -0.68
    ergus
    -0.68
    reprene
    -0.67
     Jac
    -0.67
    ger
    -0.67
    yp
    -0.67
    erb
    -0.66
    POSITIVE LOGITS
     thereafter
    1.03
     conclud
    0.90
     proport
    0.90
     contrace
    0.82
     consecut
    0.79
     upkeep
    0.74
     destro
    0.73
    utical
    0.73
     unden
    0.72
     occas
    0.72
    Activations Density 0.013%

    No Known Activations