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. 4-RES-JB
    6. 3114
    Prev
    Next
    INDEX
    Explanations

    the word "actual" within the text

    oai_token-act-pair · gpt-3.5-turbo

    the term "actual" and its context in relation to facts or reality

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

    No Comments

    Negative Logits
    wich
    -0.84
    fu
    -0.69
     Beware
    -0.68
    zy
    -0.65
     Carbuncle
    -0.64
     ashore
    -0.63
    bay
    -0.62
     Caf
    -0.62
    bye
    -0.62
    Gate
    -0.59
    POSITIVE LOGITS
    isation
    1.03
    idad
    1.00
    ITY
    0.96
    ity
    0.96
    izations
    0.95
    ignment
    0.91
    isations
    0.91
    izable
    0.88
    ité
    0.87
    aneous
    0.85
    Activations Density 0.019%

    No Known Activations