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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1686
    Prev
    Next
    INDEX
    Explanations

    the concept of compromise in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the concept of compromise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    eye
    -0.80
    NAS
    -0.68
    eyes
    -0.66
     Mighty
    -0.66
    Maker
    -0.65
    umin
    -0.65
    ril
    -0.65
     ðŁij
    -0.64
    imes
    -0.64
    nn
    -0.64
    POSITIVE LOGITS
     compromise
    4.04
     compromises
    3.08
     compromising
    1.98
     comprom
    1.67
     compromised
    1.63
     sacrifice
    1.42
     workaround
    1.20
     concessions
    1.17
     downgrade
    1.11
     modification
    1.09
    Activations Density 0.016%

    No Known Activations