© 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. 20621
    Prev
    Next
    INDEX
    Explanations

    specific mentions of political figures with emotional or controversial language

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "is" and its variations in political contexts

    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
     mutual
    -0.71
    PsyNetMessage
    -0.69
     unison
    -0.69
     membr
    -0.68
    atos
    -0.65
     membranes
    -0.64
     Crunch
    -0.64
     specialization
    -0.63
     mats
    -0.63
    YP
    -0.63
    POSITIVE LOGITS
     veto
    0.97
     appoint
    0.95
     himself
    0.93
     appointing
    0.92
     impe
    0.92
    enegger
    0.92
     pard
    0.90
     vetoed
    0.87
     sworn
    0.86
     assassinated
    0.86
    Activations Density 0.402%

    No Known Activations