© 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. 6-RES-JB
    11. 3595
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the act of protecting someone or something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of protection and safeguarding

    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
    jet
    -0.68
    ãĥ£
    -0.66
    VP
    -0.65
    LIN
    -0.65
    gom
    -0.64
    quartered
    -0.63
    LINE
    -0.61
    quart
    -0.60
     vinegar
    -0.60
    COL
    -0.59
    POSITIVE LOGITS
    ively
    1.14
    iveness
    0.96
    orate
    0.93
    atively
    0.92
    ously
    0.90
    folios
    0.89
     against
    0.82
    ably
    0.78
    dogs
    0.78
    raints
    0.78
    Activations Density 0.040%

    No Known Activations