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. 7-RES-JB
    6. 10850
    Prev
    Next
    INDEX
    Explanations

    phrases related to correspondence or communication

    oai_token-act-pair · gpt-3.5-turbo

    references to the pronoun "they" and its context in discussing groups or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CCC
    -0.76
    nl
    -0.74
    ebus
    -0.70
     Club
    -0.70
     Lisbon
    -0.68
    cephal
    -0.67
     Kinn
    -0.65
     Eleven
    -0.65
     Baron
    -0.65
    mire
    -0.64
    POSITIVE LOGITS
    're
    1.04
     originate
    1.03
     contain
    1.03
     originated
    0.96
    atically
    0.95
     expire
    0.93
     belong
    0.93
     intersect
    0.92
     contained
    0.91
     involve
    0.90
    Activations Density 0.254%

    No Known Activations