© 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. 4-RES-JB
    11. 9093
    Prev
    Next
    INDEX
    Explanations

    words related to protective barriers or defenses

    oai_token-act-pair · gpt-3.5-turbo

    mentions of protective barriers or defensive mechanisms

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

    No Comments

    Negative Logits
    gres
    -0.81
    iasco
    -0.74
     âĸº
    -0.74
    pheus
    -0.74
    cause
    -0.74
    orie
    -0.71
     Helpful
    -0.71
    graph
    -0.68
    uria
    -0.68
    colo
    -0.66
    POSITIVE LOGITS
     shields
    0.97
     shield
    0.96
    maid
    0.84
     shielding
    0.82
    heed
    0.82
    igans
    0.76
     maiden
    0.73
     shielded
    0.72
    shield
    0.71
    ades
    0.71
    Activations Density 0.008%

    No Known Activations