© 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. 8-RES-JB
    11. 12629
    Prev
    Next
    INDEX
    Explanations

    words related to criticism and evaluation

    oai_token-act-pair · gpt-3.5-turbo

    words related to fashion and the fashion industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reloaded
    -0.63
    DonaldTrump
    -0.54
    ijk
    -0.54
    ropolis
    -0.53
     Gundam
    -0.52
    andise
    -0.52
     vot
    -0.52
     Terminal
    -0.49
    aband
    -0.49
    otin
    -0.47
    POSITIVE LOGITS
     alike
    1.83
     respectively
    1.65
     versa
    0.96
     depending
    0.88
    depending
    0.83
     interchange
    0.83
     simultaneously
    0.78
     separately
    0.76
     thereof
    0.72
     accordingly
    0.72
    Activations Density 0.676%

    No Known Activations