© 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. 23102
    Prev
    Next
    INDEX
    Explanations

    the word 'of' occurring in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to different "versions" of something

    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
    urers
    -0.99
    arers
    -0.82
    rings
    -0.82
    oji
    -0.79
    ateurs
    -0.77
    cial
    -0.75
    ering
    -0.74
    ussion
    -0.73
    phasis
    -0.72
    earchers
    -0.72
    POSITIVE LOGITS
     Fortune
    0.70
     sorts
    0.68
     Flip
    0.66
     Firefox
    0.63
     theirs
    0.61
     Hast
    0.61
     Windows
    0.61
     Christianity
    0.60
     Krypt
    0.59
     PowerPoint
    0.59
    Activations Density 0.111%

    No Known Activations