© 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. 22324
    Prev
    Next
    INDEX
    Explanations

    words related to enemies or opponents

    oai_token-act-pair · gpt-3.5-turbo

    terms related to enemies or opponents

    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
     Airl
    -0.70
    ikk
    -0.68
     processed
    -0.65
    Baby
    -0.65
     Processing
    -0.64
     INS
    -0.63
    photo
    -0.62
     express
    -0.62
    Quality
    -0.61
     processing
    -0.60
    POSITIVE LOGITS
     foes
    3.29
     foe
    3.24
     adversaries
    2.88
     adversary
    2.80
     nem
    2.33
     enemies
    2.06
     antagonists
    2.02
     opponents
    1.80
     antagonist
    1.77
     rivals
    1.70
    Activations Density 0.017%

    No Known Activations