© 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. 11-RES-JB
    11. 15716
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflicts, arrests, and military operations involving different nations and security forces

    oai_token-act-pair · gpt-3.5-turbo

    references to law enforcement and military personnel involved in confrontations or arrests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bernatorial
    -0.85
    reci
    -0.68
     relevance
    -0.67
    ospels
    -0.62
    ocry
    -0.62
    Topics
    -0.62
     examples
    -0.62
    )=
    -0.61
     correspondence
    -0.60
     autobiography
    -0.60
    POSITIVE LOGITS
     wielding
    1.26
     who
    1.00
     posing
    0.94
     attempting
    0.92
     armed
    0.91
     stationed
    0.90
    who
    0.88
     guarding
    0.88
     raiding
    0.88
     pretending
    0.87
    Activations Density 0.261%

    No Known Activations