© 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. 7-RES-JB
    11. 23605
    Prev
    Next
    INDEX
    Explanations

    negations or instances where actions are not being taken

    oai_token-act-pair · gpt-3.5-turbo

    negative constructions and phrases indicating lack of action or responsibility

    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
     CST
    -0.72
    eers
    -0.70
    soDeliveryDate
    -0.70
     Mehran
    -0.70
     Valhalla
    -0.69
     Cth
    -0.67
     Geh
    -0.65
     Tant
    -0.65
     Tribune
    -0.64
     Ninth
    -0.63
    POSITIVE LOGITS
     accepting
    0.94
    paying
    0.93
    pleting
    0.93
    iating
    0.93
    angering
    0.93
     rewarding
    0.90
     agreeing
    0.90
     committing
    0.89
    having
    0.89
     engaging
    0.88
    Activations Density 0.189%

    No Known Activations