© 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. 6-RES-JB
    11. 14674
    Prev
    Next
    INDEX
    Explanations

    words related to secure storage such as "vault"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "vault"

    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
    ppo
    -0.90
    cox
    -0.85
    crow
    -0.82
    ptive
    -0.78
    glers
    -0.77
    nes
    -0.75
    zone
    -0.74
    cone
    -0.73
    mus
    -0.71
    fried
    -0.70
    POSITIVE LOGITS
    aults
    1.04
    iary
    0.87
     vault
    0.86
    lain
    0.86
    ing
    0.84
    minster
    0.80
    ault
    0.79
    gow
    0.79
    gur
    0.74
     Vault
    0.74
    Activations Density 0.036%

    No Known Activations