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. 10-RES-JB
    6. 15595
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal issues and ethical considerations

    oai_token-act-pair · gpt-3.5-turbo

    topics related to criminal behavior and legal matters

    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
    Ô
    -0.58
    ĻĤ
    -0.55
    abases
    -0.53
    plet
    -0.51
    alg
    -0.51
    Synopsis
    -0.51
    ','
    -0.51
    ÙĪ
    -0.50
    æĺ
    -0.49
    ãĤª
    -0.48
    POSITIVE LOGITS
     ensued
    1.09
     could
    1.06
     became
    1.05
     seemed
    1.05
     ensures
    1.05
     would
    1.05
     coincides
    1.04
     amounted
    1.04
     tends
    1.04
     coincided
    1.04
    Activations Density 0.752%

    No Known Activations