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. 11-RES-JB
    6. 8936
    Prev
    Next
    INDEX
    Explanations

    phrases related to various forms of communication such as ads, notifications, or surveys

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating various forms of communication and notifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xes
    -0.91
    abouts
    -0.89
    nces
    -0.84
    flows
    -0.82
    nesses
    -0.81
     fronts
    -0.77
    ls
    -0.77
    usions
    -0.75
    lees
    -0.75
    points
    -0.74
    POSITIVE LOGITS
     preferably
    1.24
     or
    0.94
     whether
    0.93
     poem
    0.92
     regardless
    0.88
     etc
    0.87
     orchestra
    0.86
    whether
    0.85
     dentist
    0.84
     irrespective
    0.84
    Activations Density 0.210%

    No Known Activations