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. 17604
    Prev
    Next
    INDEX
    Explanations

    phrases related to ensuring compliance or safety

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to oversight and assurance of actions taken

    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
     Suggest
    -0.80
    NetMessage
    -0.75
    ËĪ
    -0.74
    Reviewer
    -0.71
     suggestion
    -0.70
    ELD
    -0.67
    toggle
    -0.66
     ado
    -0.64
     Desire
    -0.63
    question
    -0.62
    POSITIVE LOGITS
     properly
    1.11
     adequately
    1.09
     complied
    1.08
     comply
    1.06
     stays
    1.02
     correctly
    0.96
     faithfully
    0.91
     adhere
    0.89
     abide
    0.87
     accurately
    0.87
    Activations Density 0.206%

    No Known Activations