© 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. 24425
    Prev
    Next
    INDEX
    Explanations

    words related to reconvening or reconfiguring

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "reconciliation" and "deconstruction"

    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
     Guilty
    -0.72
    uana
    -0.71
    utenberg
    -0.69
    UGE
    -0.68
    TPS
    -0.67
    umble
    -0.65
    aces
    -0.65
    USH
    -0.65
    ymes
    -0.64
    igans
    -0.62
    POSITIVE LOGITS
    figured
    1.23
    nect
    1.19
    fig
    1.11
    vention
    1.09
    stant
    1.08
    structed
    1.07
    struction
    1.01
    cept
    0.99
    figure
    0.98
    strate
    0.98
    Activations Density 0.060%

    No Known Activations