© 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. 6364
    Prev
    Next
    INDEX
    Explanations

    words related to challenging situations or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "struggle" in various contexts

    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
    ables
    -0.77
    ames
    -0.67
    asters
    -0.65
     Logged
    -0.65
     briefed
    -0.65
    Arch
    -0.64
     pard
    -0.63
    headers
    -0.63
    Alert
    -0.63
    Newsletter
    -0.63
    POSITIVE LOGITS
     struggle
    3.83
     struggles
    2.54
     Struggle
    2.49
     struggled
    1.69
     struggling
    1.52
     fight
    1.52
     strugg
    1.49
     battle
    1.46
     wrestle
    1.40
     clash
    1.37
    Activations Density 0.024%

    No Known Activations