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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 17758
    Prev
    Next
    INDEX
    Explanations

    characters from different languages and scripts, as well as special characters

    oai_token-act-pair · gpt-3.5-turbo

    characters or symbols used in encoding or text representation

    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
    hyde
    -0.87
     mathemat
    -0.74
    owler
    -0.73
    ufact
    -0.71
    espie
    -0.70
     ILCS
    -0.69
    esville
    -0.69
    abase
    -0.68
    ngth
    -0.68
    assic
    -0.68
    POSITIVE LOGITS
    ×Ļ×
    1.17
    IJ
    1.16
    ת
    1.14
    ׾
    1.08
    ×ķ
    1.07
    κ
    1.00
    ä¸ī
    0.98
    ãĤī
    0.98
    ×
    0.92
    ר
    0.91
    Activations Density 0.008%

    No Known Activations