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

    Neuronpedia

    Jacobian LensNEW
    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. 21076
    Prev
    Next
    INDEX
    Explanations

    specific entities, mostly related to incidents or actions taken against them

    oai_token-act-pair · gpt-3.5-turbo

    references to personal experiences or identities of individuals

    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
     Ital
    -0.67
     Cards
    -0.67
     Readers
    -0.65
     Remastered
    -0.64
     Legend
    -0.64
     VIDEOS
    -0.63
     Retirement
    -0.63
     Proced
    -0.63
     Rewards
    -0.62
     Words
    -0.61
    POSITIVE LOGITS
    soever
    1.00
     currently
    0.92
     otherwise
    0.88
     supposedly
    0.83
     previously
    0.81
    needed
    0.77
     pesky
    0.76
     belonged
    0.76
     resulted
    0.75
     allegedly
    0.75
    Activations Density 0.318%

    No Known Activations