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. 6-RES-JB
    6. 5988
    Prev
    Next
    INDEX
    Explanations

    phrases relating to providing benefits or advantages to someone or something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to benefits and advantages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.93
    LINE
    -0.67
    zona
    -0.67
    RANT
    -0.66
    âĸł
    -0.65
     throat
    -0.65
    mouth
    -0.64
    netflix
    -0.63
    IFE
    -0.63
     throats
    -0.62
    POSITIVE LOGITS
     outweigh
    0.75
     riches
    0.74
    aea
    0.70
     fortun
    0.68
    uly
    0.67
     claimants
    0.66
     resources
    0.65
     plentiful
    0.65
     wealth
    0.64
     curing
    0.63
    Activations Density 0.211%

    No Known Activations