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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 167
    Prev
    Next
    INDEX
    Explanations

    mentions of places, events, or situations where evacuation is occurring

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "evacuated" and related terms

    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
    ITH
    -0.84
    Sharp
    -0.81
     dag
    -0.78
    ith
    -0.76
     skew
    -0.71
     Signed
    -0.70
    Pattern
    -0.70
    erer
    -0.69
    cur
    -0.68
     Peer
    -0.68
    POSITIVE LOGITS
     evacuation
    3.57
     evacuated
    3.24
     evac
    3.23
     evacuate
    3.04
     quarantine
    1.40
     lockdown
    1.32
     eject
    1.28
     exodus
    1.24
     resettlement
    1.22
     relocation
    1.19
    Activations Density 0.014%

    No Known Activations