© 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. 11703
    Prev
    Next
    INDEX
    Explanations

    topics related to conflict or combat

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with combat and conflict

    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
     chrom
    -0.72
     subdiv
    -0.70
    thal
    -0.66
     peak
    -0.64
     bloom
    -0.64
     Lars
    -0.64
     clients
    -0.63
     perm
    -0.62
     guests
    -0.62
     assured
    -0.62
    POSITIVE LOGITS
     Fighting
    4.03
    Fighting
    2.62
     Fighters
    1.66
     FIGHT
    1.57
     Fighter
    1.45
    fighting
    1.42
     Combat
    1.40
     Fight
    1.36
    Fight
    1.30
     Flying
    1.28
    Activations Density 0.013%

    No Known Activations