© 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. 3-RES-JB
    11. 15067
    Prev
    Next
    INDEX
    Explanations

    characters in non-Latin alphabets at specific positions within the text

    oai_token-act-pair · gpt-3.5-turbo

    the character "ĩ" and its variations in different contexts

    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
    rette
    -0.90
     bluff
    -0.86
    raviolet
    -0.81
    ters
    -0.80
    sett
    -0.79
    ulative
    -0.78
    undai
    -0.77
    verts
    -0.76
    ilts
    -0.76
    fet
    -0.72
    POSITIVE LOGITS
    ا
    1.02
    ī
    0.98
    ĩ
    0.97
    į
    0.96
    ÑĮ
    0.96
    н
    0.96
    ĥ
    0.95
    е
    0.95
    Į
    0.92
    и
    0.90
    Activations Density 0.006%

    No Known Activations