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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 15661
    Prev
    Next
    INDEX
    Explanations

    details related to specific times and dates

    oai_token-act-pair · gpt-3.5-turbo

    references to specific numerical time or date information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tremend
    -0.88
    ¥ŀ
    -0.88
     reluct
    -0.81
     citiz
    -0.77
    querque
    -0.76
    undai
    -0.73
    achus
    -0.73
     neighb
    -0.73
     pregn
    -0.72
     happ
    -0.71
    POSITIVE LOGITS
    00
    1.28
    88
    1.10
    765
    1.08
    70
    1.04
    65
    1.03
    89
    1.03
    325
    1.02
    83
    1.02
    79
    1.01
    67
    1.01
    Activations Density 0.152%

    No Known Activations