© 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. 23098
    Prev
    Next
    INDEX
    Explanations

    specific entities or phrases related to the company Deloitte

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names associated with organizations and people

    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
    lication
    -0.64
    belt
    -0.62
    Ô
    -0.60
    prem
    -0.58
     BASE
    -0.58
     Responsibility
    -0.57
     Zhu
    -0.56
     bout
    -0.55
     IMAGES
    -0.54
     dearly
    -0.53
    POSITIVE LOGITS
    ciating
    1.20
    idated
    0.94
    icio
    0.88
    oppers
    0.76
    itte
    0.71
    oche
    0.71
    acy
    0.69
    uese
    0.68
    iflower
    0.68
    owship
    0.67
    Activations Density 0.083%

    No Known Activations