© 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. 0-RES-JB
    11. 16688
    Prev
    Next
    INDEX
    Explanations

    words associated with providing protection or defense

    oai_token-act-pair · gpt-3.5-turbo

    references to protective measures or barriers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Moz
    -0.84
     Calvin
    -0.78
     Kinder
    -0.67
    rences
    -0.67
     Bie
    -0.66
     CPC
    -0.66
     Jobs
    -0.65
     Von
    -0.65
     Recomm
    -0.65
    omin
    -0.64
    POSITIVE LOGITS
     shield
    3.43
     Shield
    3.30
     shields
    3.15
    Shield
    2.90
    shield
    2.69
     Shields
    2.47
     shielding
    2.25
     shielded
    1.84
     cloak
    1.36
     shroud
    1.28
    Activations Density 0.018%

    No Known Activations