© 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 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. 6224
    Prev
    Next
    INDEX
    Explanations

    the concept of starting or creating something from the beginning

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the concept of building or starting something from scratch

    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
     Ober
    -0.73
    relations
    -0.72
     conflic
    -0.68
    omin
    -0.67
    ossession
    -0.67
    orm
    -0.66
    agonist
    -0.65
     obesity
    -0.64
    ombs
    -0.63
     disproportionate
    -0.63
    POSITIVE LOGITS
     scratch
    1.29
     scratched
    0.99
    ratch
    0.93
    pad
    0.93
    manship
    0.87
    dot
    0.82
    lihood
    0.82
    bats
    0.81
     scratches
    0.80
    backer
    0.80
    Activations Density 0.008%

    No Known Activations