© 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. 19723
    Prev
    Next
    INDEX
    Explanations

    phrases with non-standard characters and symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols used in various contexts

    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
    hyde
    -0.81
    ngth
    -0.79
    aged
    -0.78
    alach
    -0.77
     ILCS
    -0.74
    agers
    -0.72
    esville
    -0.72
    assies
    -0.68
    aging
    -0.67
    espie
    -0.66
    POSITIVE LOGITS
    IJ
    1.23
    ת
    1.03
    ׾
    1.02
    ×Ļ×
    0.99
    ×ķ
    0.98
    ä¸ī
    0.90
    κ
    0.89
    µ
    0.89
    ĺ
    0.89
    Ĺ
    0.89
    Activations Density 0.008%

    No Known Activations