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. 16267
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "ina"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ina" within words

    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
     Phar
    -0.66
     overrun
    -0.64
     command
    -0.64
     churn
    -0.62
     kernels
    -0.61
     Command
    -0.59
     PU
    -0.59
     toes
    -0.58
     ______
    -0.58
     testers
    -0.57
    POSITIVE LOGITS
    ina
    4.26
    INA
    2.76
    inas
    2.45
    ino
    1.72
    inia
    1.69
    inal
    1.68
    rina
    1.55
    ines
    1.51
    inian
    1.49
    inos
    1.48
    Activations Density 0.015%

    No Known Activations