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. 0-RES-JB
    6. 150
    Prev
    Next
    INDEX
    Explanations

    phrases related to obtaining or possessing something

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "attain" or related to obtaining something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     breathing
    -0.62
     retreat
    -0.61
     repeating
    -0.61
     slicing
    -0.61
     acceleration
    -0.60
     rotating
    -0.60
     anarchism
    -0.59
     accelerated
    -0.59
     braking
    -0.59
     minutes
    -0.59
    POSITIVE LOGITS
    tain
    4.81
    tained
    3.51
    tains
    3.24
    taining
    2.86
    TAIN
    2.08
    tainment
    1.57
    gins
    1.11
    rouse
    1.03
    prises
    1.02
    tan
    1.01
    Activations Density 0.022%

    No Known Activations