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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 20945
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols placed before text strings

    oai_token-act-pair · gpt-3.5-turbo

    musical elements or references in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mous
    -0.89
     ASC
    -0.80
    anwhile
    -0.80
    theless
    -0.79
     Schn
    -0.76
     tremend
    -0.75
     princ
    -0.74
     sacrific
    -0.72
     eleph
    -0.72
     shroud
    -0.70
    POSITIVE LOGITS
    ľ
    1.71
    ł
    1.39
    Ŀ
    1.35
    ¡
    1.35
    Ķ
    1.34
    Ł
    1.33
    ª
    1.29
    ¦
    1.28
    ¼
    1.27
    ĺ
    1.27
    Activations Density 0.159%

    No Known Activations