© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5052
    Prev
    Next
    INDEX
    Explanations

    phrases related to political or administration activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant events or actions within a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     depends
    -0.66
    pires
    -0.65
     varies
    -0.61
     relies
    -0.56
    gencies
    -0.55
     requires
    -0.55
     tells
    -0.55
    obi
    -0.54
     helps
    -0.54
     hangs
    -0.54
    POSITIVE LOGITS
    terday
    0.71
    Jews
    0.62
     yesterday
    0.60
     Communists
    0.55
     fiasco
    0.54
    Russ
    0.53
    during
    0.53
     Communism
    0.53
     beforehand
    0.52
     Bulgar
    0.51
    Activations Density 2.081%

    No Known Activations