© 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. 846
    Prev
    Next
    INDEX
    Explanations

    phrases related to emergency situations and rescue operations

    oai_token-act-pair · gpt-3.5-turbo

    urgent calls for help and rescue situations

    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
    Ô
    -0.73
    hibit
    -0.72
    ahan
    -0.71
    Transaction
    -0.69
     infringing
    -0.69
     Assass
    -0.68
     counterfe
    -0.68
    ħĭ
    -0.66
     Topic
    -0.66
     dissertation
    -0.66
    POSITIVE LOGITS
     rescue
    1.60
     resc
    1.59
     stret
    1.51
     rescued
    1.44
     rescuing
    1.34
     Rescue
    1.29
     raft
    1.23
     paramedics
    1.22
     stranded
    1.20
     resusc
    1.16
    Activations Density 0.522%

    No Known Activations