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. 8-RES-JB
    6. 21271
    Prev
    Next
    INDEX
    Explanations

    instances of the word "naturally" used in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the word "naturally" and variations or phrases that indicate natural occurrences or tendencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eworks
    -0.74
    eters
    -0.71
    seless
    -0.71
    berman
    -0.67
    anmar
    -0.66
    andals
    -0.66
     Millennium
    -0.65
    mented
    -0.63
    raph
    -0.62
     Patients
    -0.62
    POSITIVE LOGITS
     occurring
    0.99
    istic
    0.90
    istically
    0.85
     instinct
    0.81
    occ
    0.80
     combust
    0.80
    iste
    0.78
     grav
    0.76
     progression
    0.76
     arises
    0.75
    Activations Density 0.053%

    No Known Activations