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. 16964
    Prev
    Next
    INDEX
    Explanations

    past tense verbs indicating personal growth or experiences

    oai_token-act-pair · gpt-3.5-turbo

    variations of the verb "grow," particularly in the context of personal development or upbringing

    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
     Decoder
    -0.78
    issors
    -0.72
    Universal
    -0.69
    zzi
    -0.67
    ibrary
    -0.62
     Implementation
    -0.62
    esson
    -0.62
     Mub
    -0.61
    DAQ
    -0.61
    ":"","
    -0.61
    POSITIVE LOGITS
     accustomed
    1.24
     weary
    1.13
     tired
    1.07
    ups
    1.06
     bored
    1.05
     up
    1.05
     pains
    0.98
     restless
    0.96
     taller
    0.94
     disillusion
    0.92
    Activations Density 0.039%

    No Known Activations