© 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. 9155
    Prev
    Next
    INDEX
    Explanations

    terms related to opinions, judgments, and qualifications

    oai_token-act-pair · gpt-3.5-turbo

    phrases or references to groups of people collectively

    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
    isal
    -0.74
    cation
    -0.68
    mania
    -0.66
    llah
    -0.66
    pex
    -0.66
    dden
    -0.65
    etheless
    -0.65
    aml
    -0.64
    mire
    -0.64
    ertodd
    -0.63
    POSITIVE LOGITS
     themselves
    1.25
     selves
    1.08
    selves
    1.04
     helmets
    0.79
    MpServer
    0.78
     individually
    0.77
     uniforms
    0.77
     mouths
    0.76
     necks
    0.72
     jointly
    0.71
    Activations Density 0.858%

    No Known Activations