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. 11-RES-JB
    6. 4305
    Prev
    Next
    INDEX
    Explanations

    verbs related to the impact or influence of certain actions or circumstances on emotions or physical well-being

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to emotional and physical well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    DragonMagazine
    -0.90
    ãĥ´ãĤ¡
    -0.85
     VID
    -0.75
    ãĤ´ãĥ³
    -0.72
    senal
    -0.71
     Unsure
    -0.71
    DAQ
    -0.69
     Cosponsors
    -0.66
    psc
    -0.66
    EngineDebug
    -0.65
    POSITIVE LOGITS
     oneself
    1.47
     individuals
    1.28
     someone
    1.27
     participants
    1.22
     your
    1.10
     patients
    1.09
     caregivers
    1.07
     learners
    1.07
     pupils
    1.07
     students
    1.05
    Activations Density 0.581%

    No Known Activations