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. 15811
    Prev
    Next
    INDEX
    Explanations

    words related to legal and law enforcement actions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of actions involving social interactions or relationships

    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
     groundbreaking
    -0.77
     DevOnline
    -0.71
     International
    -0.69
     unparalleled
    -0.66
     Peak
    -0.66
     Comprehensive
    -0.64
     Bever
    -0.64
     landmark
    -0.64
     Featured
    -0.63
     Pipeline
    -0.63
    POSITIVE LOGITS
    they
    1.19
     dont
    1.11
     THEN
    1.00
    then
    0.99
     THEY
    0.98
    morrow
    0.93
     didnt
    0.92
     obey
    0.89
     doesnt
    0.89
    cause
    0.89
    Activations Density 0.677%

    No Known Activations