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. 3-RES-JB
    6. 14056
    Prev
    Next
    INDEX
    Explanations

    words related to chemical elements, especially those ending in '-ium'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of elements and compounds, particularly those containing "ium"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.98
    à©
    -0.80
    things
    -0.80
     PsyNet
    -0.79
    stories
    -0.76
    ãĥ¯ãĥ³
    -0.75
     à¨
    -0.71
    nee
    -0.70
    ãģį
    -0.67
    Offline
    -0.65
    POSITIVE LOGITS
     tremend
    1.22
     chloride
    0.96
     oxide
    0.90
    osate
    0.87
     dioxide
    0.84
    idium
    0.76
    fal
    0.75
    ium
    0.74
    uria
    0.73
    eus
    0.73
    Activations Density 0.013%

    No Known Activations