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. 2-RES-JB
    6. 4979
    Prev
    Next
    INDEX
    Explanations

    instances of the word "actual"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "actual" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wich
    -0.96
     ashore
    -0.82
    fu
    -0.72
    nan
    -0.69
    bye
    -0.69
    lain
    -0.68
    VK
    -0.68
    heid
    -0.66
    hire
    -0.66
    VC
    -0.65
    POSITIVE LOGITS
    ignment
    0.95
    isation
    0.91
    izations
    0.86
    idad
    0.82
    istic
    0.78
    isations
    0.77
    ITY
    0.76
    ity
    0.75
    aneous
    0.74
    ities
    0.72
    Activations Density 0.013%

    No Known Activations