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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3391
    Prev
    Next
    INDEX
    Explanations

    phrases related to software features and functions

    oai_token-act-pair · gpt-3.5-turbo

    high-frequency definite articles indicating specific features or components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebook
    -0.75
    abuse
    -0.73
    ¶
    -0.70
    elo
    -0.70
    esters
    -0.67
    votes
    -0.66
    athon
    -0.65
    clerosis
    -0.63
     nowhere
    -0.63
    abilia
    -0.62
    POSITIVE LOGITS
     following
    1.78
     same
    1.25
     usual
    1.25
     aforementioned
    1.23
     simplest
    1.03
     widest
    1.03
     requisite
    1.02
     ability
    0.97
     possibility
    0.93
     finest
    0.90
    Activations Density 0.365%

    No Known Activations