© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-JB
    11. 5370
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to branding or rebranding

    oai_token-act-pair · gpt-3.5-turbo

    references to branding and branded products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.74
    rero
    -0.66
    abama
    -0.65
    athetic
    -0.65
    vati
    -0.65
    ettel
    -0.65
     Rutherford
    -0.65
    otos
    -0.64
    allel
    -0.63
    ippi
    -0.63
    POSITIVE LOGITS
     branded
    1.10
     branding
    0.98
    ovan
    0.91
    ging
    0.89
    branded
    0.86
    brand
    0.84
    zag
    0.79
    iances
    0.78
    interstitial
    0.76
    wcs
    0.75
    Activations Density 0.009%

    No Known Activations