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. 6-RES-JB
    6. 1393
    Prev
    Next
    INDEX
    Explanations

    the word "actual" appearing in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    the word "actual" and its various forms, indicating a focus on reality or factual statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wich
    -0.68
    fu
    -0.68
     ashore
    -0.67
    bay
    -0.66
     Beware
    -0.65
     Carbuncle
    -0.63
    lust
    -0.63
    zy
    -0.63
    oner
    -0.62
    limit
    -0.62
    POSITIVE LOGITS
    isation
    1.02
    ity
    1.01
    izations
    1.01
    ITY
    0.99
    izable
    0.98
    idad
    0.98
    ities
    0.91
    ignment
    0.89
    isations
    0.88
    ité
    0.85
    Activations Density 0.025%

    No Known Activations