© 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. 2-RES-JB
    11. 18457
    Prev
    Next
    INDEX
    Explanations

    specific numerical patterns

    oai_token-act-pair · gpt-3.5-turbo

    numerical representations of time and numerical data in a record or report format

    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
    ĸļ
    -0.98
    ascus
    -0.92
     tremend
    -0.86
    atis
    -0.85
    senal
    -0.77
    undai
    -0.72
     recip
    -0.72
    ¥ŀ
    -0.71
    ongyang
    -0.71
    etheless
    -0.71
    POSITIVE LOGITS
    th
    0.96
    20
    0.84
    55
    0.83
    82
    0.83
    50
    0.83
    85
    0.83
    83
    0.83
    400
    0.82
    66
    0.82
    75
    0.81
    Activations Density 0.033%

    No Known Activations