Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 16250
    Prev
    Next
    INDEX
    Explanations

    information related to emergency situations, evacuations, and closures

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to emergency situations and evacuations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Inher
    -0.85
     immortality
    -0.81
     autobi
    -0.76
     monog
    -0.76
     Dating
    -0.76
     bragging
    -0.76
     autobiography
    -0.75
     Invention
    -0.75
     immortal
    -0.75
     hegemony
    -0.75
    POSITIVE LOGITS
     evacuated
    1.38
     evacuation
    1.28
     evac
    1.13
     evacuate
    1.08
     emergency
    1.05
     ambul
    1.03
     crews
    0.98
     precaution
    0.97
    EMS
    0.97
     closures
    0.96
    Activations Density 0.951%

    No Known Activations