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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-RES-JB
    6. 17429
    Prev
    Next
    INDEX
    Explanations

    words related to digging or excavating

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "dug" and related concepts of excavating or uncovering

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

    No Comments

    Negative Logits
     Leilan
    -0.75
     Blueprint
    -0.71
     istg
    -0.68
    cream
    -0.68
     constitu
    -0.66
    Kenn
    -0.66
     Strait
    -0.66
    Thomas
    -0.63
    cia
    -0.63
    javascript
    -0.63
    POSITIVE LOGITS
     dug
    1.09
     digging
    1.03
     dig
    1.00
     trenches
    0.98
     digs
    0.93
    ongs
    0.87
    itial
    0.84
     holes
    0.81
     Dug
    0.80
     graves
    0.80
    Activations Density 0.009%

    No Known Activations