© 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. 1-RES-JB
    11. 3108
    Prev
    Next
    INDEX
    Explanations

    phrases containing the suffix "du."

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the substring 'du' within words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Policies
    -0.70
     Units
    -0.69
     Conditions
    -0.69
     Fired
    -0.67
    ocene
    -0.67
     ages
    -0.66
     Limits
    -0.66
     Angels
    -0.65
     Wanted
    -0.65
     Methods
    -0.64
    POSITIVE LOGITS
    du
    1.11
    gment
    0.99
    pling
    0.93
    plets
    0.88
    plet
    0.86
    ples
    0.85
    ffer
    0.82
    iple
    0.82
    pee
    0.82
    pload
    0.81
    Activations Density 0.005%

    No Known Activations