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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 15199
    Prev
    Next
    INDEX
    Explanations

    terms related to defense and protection

    oai_token-act-pair · gpt-3.5-turbo

    terms related to defense and protection mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idays
    -0.70
     Parenthood
    -0.69
    ļéĨĴ
    -0.68
    leaf
    -0.67
    çīĪ
    -0.66
    ANN
    -0.65
     Kinn
    -0.65
    translation
    -0.65
    LIN
    -0.63
     Fever
    -0.62
    POSITIVE LOGITS
     against
    1.44
    against
    1.22
     Against
    1.03
    ously
    0.88
     turrets
    0.86
     protects
    0.86
     AGA
    0.81
     guarding
    0.81
     defences
    0.79
     defenses
    0.78
    Activations Density 0.125%

    No Known Activations