© 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. 4-RES-JB
    11. 14643
    Prev
    Next
    INDEX
    Explanations

    instances of the word "accounted for" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "accounted for" in various contexts

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

    No Comments

    Negative Logits
    Lab
    -0.76
    soever
    -0.74
    BuyableInstoreAndOnline
    -0.72
    GR
    -0.72
    EL
    -0.70
    LAB
    -0.69
    lime
    -0.68
    Hub
    -0.68
    é¾
    -0.68
    DEM
    -0.67
    POSITIVE LOGITS
    bidden
    0.88
     centuries
    0.87
    gotten
    0.84
    gery
    0.77
     millennia
    0.70
    lain
    0.70
     subsistence
    0.69
    vich
    0.67
    geries
    0.66
    ainment
    0.65
    Activations Density 0.078%

    No Known Activations