© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 2254
    Prev
    Next
    INDEX
    Explanations

    mentions of civilians affected by conflict or war-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to civilians in conflict situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ologies
    -0.84
    href
    -0.80
    Magikarp
    -0.78
    Stud
    -0.75
    Smith
    -0.73
    Vert
    -0.72
    SourceFile
    -0.71
    ology
    -0.71
    OLOGY
    -0.68
    Lear
    -0.67
    POSITIVE LOGITS
     fleeing
    0.93
     massac
    0.81
     casualties
    0.80
     overboard
    0.78
     evacuated
    0.78
     slain
    0.77
     flee
    0.77
     displaced
    0.77
     aged
    0.76
    folk
    0.76
    Activations Density 0.021%

    No Known Activations