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. 10-RES-JB
    6. 9584
    Prev
    Next
    INDEX
    Explanations

    the word "because" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "because."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pione
    -0.75
     exting
    -0.72
    vous
    -0.69
    pmwiki
    -0.68
    Ď
    -0.67
    wn
    -0.67
    À
    -0.67
    ā
    -0.66
    ė
    -0.66
    	
    -0.66
    POSITIVE LOGITS
     otherwise
    1.16
     frankly
    1.02
     they
    1.00
     nobody
    0.98
     it
    0.98
     hey
    0.97
     honestly
    0.96
     unlike
    0.93
     there
    0.93
     obviously
    0.91
    Activations Density 0.091%

    No Known Activations