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. 12402
    Prev
    Next
    INDEX
    Explanations

    words related to precious stones

    oai_token-act-pair · gpt-3.5-turbo

    references to gemstones or metaphorical representations of valuable elements

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Grounds
    -0.75
     Parties
    -0.68
    ŃĶ
    -0.67
     Pace
    -0.66
    lihood
    -0.66
     Prob
    -0.65
     Roose
    -0.64
     Consent
    -0.64
     Desire
    -0.63
     Dragonbound
    -0.62
    POSITIVE LOGITS
    stones
    1.57
    stone
    1.35
     gems
    1.08
     gem
    1.00
    bl
    0.83
    oche
    0.82
    cit
    0.81
    istry
    0.81
    cellent
    0.79
     jewels
    0.78
    Activations Density 0.016%

    No Known Activations