© 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. 2-RES-JB
    11. 1451
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of a protective barrier or defense mechanism

    oai_token-act-pair · gpt-3.5-turbo

    references to protective barriers or defenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PM
    -0.80
    cause
    -0.72
    OTAL
    -0.70
     Helpful
    -0.69
    gres
    -0.68
    eph
    -0.67
    uria
    -0.67
     Judicial
    -0.66
    ETA
    -0.66
    orie
    -0.64
    POSITIVE LOGITS
     shield
    1.13
     shields
    1.10
     shielding
    0.94
    maid
    0.83
     maiden
    0.82
    heed
    0.82
    buster
    0.80
     curtain
    0.78
     shielded
    0.77
    igans
    0.77
    Activations Density 0.006%

    No Known Activations