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. 3-RES-JB
    6. 19551
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names in sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" at the beginning of phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Deal
    -0.68
    Availability
    -0.67
    interstitial
    -0.67
    Cause
    -0.63
    Reward
    -0.63
    terness
    -0.61
    num
    -0.61
    Upload
    -0.59
    UF
    -0.58
    Tomorrow
    -0.57
    POSITIVE LOGITS
     however
    1.40
     meanwhile
    1.25
     huh
    1.14
     though
    1.00
     moreover
    1.00
     albeit
    0.91
     although
    0.87
     unsurprisingly
    0.84
     therefore
    0.83
     alas
    0.83
    Activations Density 1.126%

    No Known Activations