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. 13068
    Prev
    Next
    INDEX
    Explanations

    text containing a mix of special characters that don't form coherent words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    special characters or non-standard symbols

    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
     guiActiveUn
    -0.80
     Thumbnails
    -0.79
     GOODMAN
    -0.78
     Constantine
    -0.73
     Ada
    -0.72
    itaire
    -0.70
     Franch
    -0.69
    ashtra
    -0.69
    minster
    -0.67
    osaurs
    -0.66
    POSITIVE LOGITS
    §
    1.39
    Ĥ
    1.32
    ¬¼
    1.32
    ¹
    1.30
    ¶
    1.23
    ²
    1.21
    ´
    1.19
    ĭ
    1.16
    ¸
    1.15
    Į
    1.15
    Activations Density 0.006%

    No Known Activations