© 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. 3-RES-JB
    6. 22856
    Prev
    Next
    INDEX
    Explanations

    references to "365", often related to Microsoft Office

    oai_token-act-pair · gpt-3.5-turbo

    references to the number 365 and related numerical identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geon
    -0.81
    iewicz
    -0.75
     Eisen
    -0.73
    asher
    -0.73
    oly
    -0.70
    isen
    -0.68
    oxin
    -0.66
    lda
    -0.66
     thirds
    -0.66
    umbling
    -0.65
    POSITIVE LOGITS
    ertodd
    0.96
     ILCS
    0.94
    cffff
    0.94
    365
    0.89
     365
    0.79
    iencies
    0.78
    æ³
    0.77
    cies
    0.76
    à¼
    0.73
    rir
    0.72
    Activations Density 0.014%

    No Known Activations