© 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. 2-RES-JB
    11. 23843
    Prev
    Next
    INDEX
    Explanations

    references to the word "iron" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to iron and its various uses or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lished
    -0.75
     FTA
    -0.66
     Payment
    -0.63
    akening
    -0.60
     Disorder
    -0.60
    erker
    -0.59
     Printed
    -0.59
     Polk
    -0.59
     Wanted
    -0.59
    earch
    -0.59
    POSITIVE LOGITS
    clad
    0.99
    iron
    0.90
    ically
    0.88
    culosis
    0.83
    bat
    0.80
    erie
    0.77
    ãĤ¤ãĥĪ
    0.74
    worm
    0.73
    bj
    0.73
    BuyableInstoreAndOnline
    0.72
    Activations Density 0.002%

    No Known Activations