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. 1-RES-JB
    6. 17425
    Prev
    Next
    INDEX
    Explanations

    references to software development dependencies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dependencies, particularly in technical or social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iday
    -0.84
    gm
    -0.78
    apers
    -0.76
    tell
    -0.75
    past
    -0.73
    issions
    -0.71
    iman
    -0.71
    isers
    -0.70
    ells
    -0.69
    ission
    -0.69
    POSITIVE LOGITS
     dependency
    1.28
    encies
    1.24
     dependencies
    1.09
    depend
    0.89
     withd
    0.89
     destro
    0.82
     Depend
    0.79
     strugg
    0.79
    ency
    0.77
     coerc
    0.77
    Activations Density 0.012%

    No Known Activations