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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 9663
    Prev
    Next
    INDEX
    Explanations

    Cyrillic characters

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific characters or symbols, likely indicating encoding issues or special characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    20439
    -0.70
    ORED
    -0.67
     Starr
    -0.67
     guiActiveUnfocused
    -0.65
    anwhile
    -0.64
     Bain
    -0.64
     anecdotes
    -0.63
    oleon
    -0.63
     Beckham
    -0.63
    theless
    -0.63
    POSITIVE LOGITS
    ¾
    1.35
    ¸
    1.33
    ¡
    1.30
    ļ
    1.29
    ²
    1.28
    ¼
    1.27
    º
    1.27
    ij
    1.26
    IJ
    1.26
    ¿
    1.26
    Activations Density 0.007%

    No Known Activations