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. 21330
    Prev
    Next
    INDEX
    Explanations

    words related to names that end with 'ak'

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to the concept of "acknowledgment."

    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
     numbered
    -0.66
     span
    -0.66
     polyg
    -0.65
     expectancy
    -0.62
     content
    -0.61
     grandchildren
    -0.61
     laps
    -0.61
     demographics
    -0.60
     grooming
    -0.59
     positively
    -0.59
    POSITIVE LOGITS
    ak
    3.95
    aks
    2.53
    akable
    1.94
    AK
    1.94
    akov
    1.88
    aky
    1.77
    akin
    1.76
    aked
    1.73
    ako
    1.71
    aking
    1.69
    Activations Density 0.020%

    No Known Activations