Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 16020
    Prev
    Next
    INDEX
    Explanations

    Cyrillic and accented Latin characters

    oai_token-act-pair · gpt-3.5-turbo

    character sequences or patterns, potentially signifying encoding errors or specific characters in a different language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortium
    -0.77
    onomy
    -0.70
     bearer
    -0.67
     Grayson
    -0.65
    elope
    -0.65
     athlet
    -0.64
     Brach
    -0.63
     admission
    -0.62
    xon
    -0.61
    RAY
    -0.60
    POSITIVE LOGITS
    ³
    1.67
    ¹
    1.66
    ¼
    1.63
    ²
    1.63
    º
    1.62
    ±
    1.59
    ¶
    1.53
    ´
    1.50
    ¡
    1.39
    ¿
    1.39
    Activations Density 0.014%

    No Known Activations