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. 12-RES-JB
    6. 14507
    Prev
    Next
    INDEX
    Explanations

    verbs related to arranging or scheduling actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of scheduling or rescheduling events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.90
    iri
    -0.86
     Carbuncle
    -0.84
    ãĥİ
    -0.83
    iris
    -0.82
    ira
    -0.80
    umar
    -0.78
    Isa
    -0.78
    Thom
    -0.77
     Odyssey
    -0.76
    POSITIVE LOGITS
     Che
    2.56
    Che
    2.29
     che
    1.90
    che
    1.80
    Chel
    1.70
     Cheng
    1.39
     Chester
    1.29
     chees
    1.28
     Cheese
    1.26
     Whe
    1.24
    Activations Density 0.255%

    No Known Activations