© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3277
    Prev
    Next
    INDEX
    Explanations

    phrases related to protection, security, and proxy usage

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    concepts related to protection and defense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omin
    -0.69
    umo
    -0.69
    åŃ
    -0.66
    uscript
    -0.65
    favorite
    -0.64
    urious
    -0.64
     Crowley
    -0.64
     dissatisf
    -0.64
    ecided
    -0.63
     Hastings
    -0.63
    POSITIVE LOGITS
     protection
    1.85
     defenses
    1.74
     defences
    1.67
     protect
    1.64
    protection
    1.63
     defense
    1.61
     protecting
    1.59
     protects
    1.58
     shield
    1.57
    protect
    1.56
    Activations Density 0.551%

    No Known Activations