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. 8-RES-JB
    6. 19162
    Prev
    Next
    INDEX
    Explanations

    words related to aspirations or goals

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the concept of "becoming" or transformation into a certain role or status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ongyang
    -0.84
    ramid
    -0.74
     goodness
    -0.71
    ength
    -0.68
    pressure
    -0.66
    ciating
    -0.63
    ages
    -0.62
    bell
    -0.62
    rule
    -0.61
    duty
    -0.61
    POSITIVE LOGITS
     acquainted
    1.10
     accustomed
    1.10
     extinct
    1.04
     aware
    0.99
     entangled
    0.99
     embroiled
    0.96
     addicted
    0.89
     obsessed
    0.87
     eligible
    0.86
     unemploy
    0.84
    Activations Density 0.056%

    No Known Activations