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. 8-RES-JB
    6. 227
    Prev
    Next
    INDEX
    Explanations

    future plans or possibilities mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to bids, runs, and proposals in a political or entertainment context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verbs
    -0.67
     stere
    -0.59
     Tycoon
    -0.56
     merchants
    -0.56
     Gleaming
    -0.55
    wick
    -0.54
     fractions
    -0.54
    ongs
    -0.53
     Boone
    -0.53
     Sina
    -0.53
    POSITIVE LOGITS
     someday
    1.27
     anytime
    1.09
     sooner
    0.99
     sometime
    0.95
     ASAP
    0.95
     soon
    0.92
     conclud
    0.83
    ossier
    0.83
     showdown
    0.74
     hereafter
    0.73
    Activations Density 0.511%

    No Known Activations