© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 10443
    Prev
    Next
    INDEX
    Explanations

    words related to various chemical elements or compounds, particularly those ending in 'ium'

    oai_token-act-pair · gpt-3.5-turbo

    references to various chemical elements, particularly those ending with 'ium'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.98
    à©
    -0.81
     PsyNet
    -0.81
    EStreamFrame
    -0.81
    natureconservancy
    -0.77
    things
    -0.75
    soType
    -0.72
     à¨
    -0.70
    isSpecialOrderable
    -0.69
    ãģį
    -0.68
    POSITIVE LOGITS
     tremend
    1.17
    ium
    1.11
    idium
    0.90
     oxide
    0.83
     chloride
    0.79
    osate
    0.79
    peria
    0.78
    eus
    0.77
    ophon
    0.75
     plutonium
    0.75
    Activations Density 0.009%

    No Known Activations