© 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. 0-RES-JB
    11. 16466
    Prev
    Next
    INDEX
    Explanations

    words related to preservation or protection

    oai_token-act-pair · gpt-3.5-turbo
    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
     Zig
    -0.72
    wire
    -0.72
     breakout
    -0.69
    oad
    -0.69
    GW
    -0.68
     Nigeria
    -0.67
     Narc
    -0.67
     BS
    -0.67
    uno
    -0.65
    ãĥĨ
    -0.65
    POSITIVE LOGITS
     preserved
    3.27
     preservation
    2.85
     preserves
    2.55
     preserving
    2.54
     preserve
    2.19
     Preservation
    2.10
     conserv
    1.32
     restored
    1.29
     retained
    1.24
     reconstructed
    1.20
    Activations Density 0.029%

    No Known Activations