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. 0-RES-JB
    6. 3229
    Prev
    Next
    INDEX
    Explanations

    references to the word "Discovery"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of 'discovery'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Slim
    -0.68
     Spell
    -0.67
     votes
    -0.67
    om
    -0.67
    Spell
    -0.67
    mor
    -0.66
    vote
    -0.64
    votes
    -0.61
    gun
    -0.61
    otte
    -0.61
    POSITIVE LOGITS
     Discovery
    3.36
    iscovery
    1.20
     discovery
    1.07
     Voyager
    0.94
     Prometheus
    0.92
     Enterprise
    0.91
     Curiosity
    0.91
     NX
    0.85
     Venture
    0.84
     Pioneer
    0.81
    Activations Density 0.002%

    No Known Activations