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. 15119
    Prev
    Next
    INDEX
    Explanations

    instances of the word "private" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to private or special meetings and gatherings

    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
    ologies
    -0.96
    tics
    -0.94
    stories
    -0.94
    ences
    -0.94
    types
    -0.91
    osaurs
    -0.89
    hops
    -0.87
    rings
    -0.87
    Tags
    -0.84
    iments
    -0.84
    POSITIVE LOGITS
     memorandum
    1.02
     advisory
    1.02
     version
    0.93
     panel
    0.92
     questionnaire
    0.92
     statement
    0.91
     hotline
    0.91
     programme
    0.90
     audit
    0.90
     arrangement
    0.90
    Activations Density 0.408%

    No Known Activations