© 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. 8-RES-JB
    11. 3418
    Prev
    Next
    INDEX
    Explanations

    words related to significant changes or shifts in thinking or perspective

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to shifts in paradigms or fundamental changes in systems

    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
    itarian
    -0.74
    é¾
    -0.72
    llah
    -0.72
    sports
    -0.69
    Ñĭ
    -0.67
    itals
    -0.67
     DISTRICT
    -0.67
    IENCE
    -0.67
     Cosponsors
    -0.66
     Murd
    -0.65
    POSITIVE LOGITS
    avior
    0.88
    velop
    0.81
    avi
    0.80
    OPLE
    0.74
    anger
    0.71
    rums
    0.68
    mann
    0.68
    lers
    0.68
    Í
    0.67
    rop
    0.67
    Activations Density 0.115%

    No Known Activations