© 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. 22380
    Prev
    Next
    INDEX
    Explanations

    words related to conflicts or conflict resolution

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Conflict" and related terms

    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
     retarded
    -0.73
    oly
    -0.66
     fet
    -0.64
    erman
    -0.63
     audible
    -0.63
     asleep
    -0.63
     insane
    -0.62
     deaf
    -0.62
     Whitman
    -0.61
    buff
    -0.60
    POSITIVE LOGITS
     Conflict
    3.18
    Conf
    1.61
     Cov
    1.20
    CI
    1.12
    ihilation
    1.01
    ikh
    1.00
     Conquest
    0.95
     Struggle
    0.94
     Smash
    0.92
    IRC
    0.92
    Activations Density 0.037%

    No Known Activations