Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 16673
    Prev
    Next
    INDEX
    Explanations

    mentions of something being special in some context

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "special."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Special

    No Comments

    Negative Logits
     Twain
    -0.69
     Ri
    -0.66
    anon
    -0.65
     Giul
    -0.65
     Cah
    -0.63
    Ķ
    -0.63
     Cao
    -0.62
    amus
    -0.61
    Į
    -0.60
    ·
    -0.60
    POSITIVE LOGITS
    ised
    1.15
    ties
    1.00
    izations
    0.96
    isations
    0.95
    isable
    0.90
    ized
    0.89
    marine
    0.84
    ities
    0.83
    isal
    0.81
    atural
    0.81
    Activations Density 0.022%

    No Known Activations