© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 10034
    Prev
    Next
    INDEX
    Explanations

    phrases related to the launching of campaigns, investigations, and complaints

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "launch" and its variations, indicating initiation of actions or projects

    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
    emo
    -0.65
    Score
    -0.64
    oping
    -0.58
    uala
    -0.57
    eping
    -0.57
    esan
    -0.55
    avering
    -0.55
    Son
    -0.55
    etry
    -0.55
    olin
    -0.55
    POSITIVE LOGITS
     anew
    1.11
     INTO
    0.88
     into
    0.79
     Operation
    0.78
    launch
    0.77
     campaigns
    0.77
     explor
    0.76
     investigations
    0.75
     probes
    0.75
    igate
    0.75
    Activations Density 0.054%

    No Known Activations