© 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. 20414
    Prev
    Next
    INDEX
    Explanations

    words related to preferences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to preferences and choices

    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
    manship
    -0.76
    mberg
    -0.74
    wordpress
    -0.67
    tics
    -0.67
    angel
    -0.66
    STD
    -0.66
    bane
    -0.66
    meal
    -0.65
     Bam
    -0.65
    icago
    -0.65
    POSITIVE LOGITS
     preferences
    1.06
     favoring
    0.96
     preference
    0.86
     favoured
    0.85
    eering
    0.82
     favored
    0.77
     pane
    0.77
    ļéĨĴ
    0.76
     favors
    0.75
    ately
    0.75
    Activations Density 0.032%

    No Known Activations