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. 13224
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, perhaps related to news or events

    oai_token-act-pair · gpt-3.5-turbo

    end punctuation marks, particularly periods

    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
     challeng
    -0.87
     taxing
    -0.76
     workspace
    -0.75
     allowance
    -0.73
     recons
    -0.71
     obsolete
    -0.71
     scaven
    -0.71
     farmland
    -0.69
     substit
    -0.69
     enthusi
    -0.69
    POSITIVE LOGITS
     His
    1.07
     Their
    1.02
     Though
    1.02
     Initially
    1.02
     Interestingly
    0.99
     He
    0.98
     Shortly
    0.96
     Apparently
    0.95
     Eventually
    0.95
     Together
    0.94
    Activations Density 0.395%

    No Known Activations