© 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. 5520
    Prev
    Next
    INDEX
    Explanations

    phrases related to official stances or positions on various subjects

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "on," particularly in political or positional contexts

    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
    ennes
    -0.80
    ults
    -0.72
    ::::::::
    -0.68
    ENTS
    -0.67
    ï¸ı
    -0.67
    SourceFile
    -0.67
    MODE
    -0.67
    ARM
    -0.65
    BILITIES
    -0.65
    ACT
    -0.65
    POSITIVE LOGITS
     behalf
    1.65
    erous
    1.02
    yx
    0.96
    etheless
    0.94
     steroids
    0.92
    etime
    0.89
     Capitol
    0.87
     matters
    0.86
    shore
    0.85
    site
    0.85
    Activations Density 0.233%

    No Known Activations