© 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. 0-RES-JB
    11. 16496
    Prev
    Next
    INDEX
    Explanations

    instances of the emergency number "911" being mentioned in texts

    oai_token-act-pair · gpt-3.5-turbo
    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
     practise
    -0.70
     fermented
    -0.65
     enchanted
    -0.62
    anga
    -0.62
    åĮ
    -0.60
     attached
    -0.60
     ve
    -0.60
    BILITY
    -0.59
    hig
    -0.59
    ench
    -0.59
    POSITIVE LOGITS
     911
    3.96
    911
    2.57
     999
    1.85
     dispatcher
    1.31
     311
    1.24
     EMS
    1.14
     CPR
    1.12
     920
    1.10
     SWAT
    1.09
     dispatch
    1.08
    Activations Density 0.026%

    No Known Activations