© 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. 9-RES-JB
    11. 14830
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflict, war, and military interventions

    oai_token-act-pair · gpt-3.5-turbo

    references to the Bosnian Civil War and aspects related to peacekeeping and violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    whatever
    -0.81
     theirs
    -0.76
    Thankfully
    -0.74
     whoever
    -0.73
     thankfully
    -0.73
    \/\/
    -0.72
    Luckily
    -0.70
    Secondly
    -0.69
     luckily
    -0.69
    Ire
    -0.68
    POSITIVE LOGITS
     Evaluation
    1.05
     Predict
    0.91
     Effects
    0.90
     Compar
    0.90
     Factors
    0.89
     Perspect
    0.88
     Statistical
    0.88
     Differences
    0.88
     Evidence
    0.85
     Experimental
    0.85
    Activations Density 0.353%

    No Known Activations