© 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. 8925
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of creating or establishing something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences related to the concept of "formation."

    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
    verse
    -0.71
    hou
    -0.64
    consumer
    -0.63
    cedented
    -0.62
    Consumer
    -0.62
    bledon
    -0.61
    pez
    -0.61
    Marvel
    -0.61
    bi
    -0.61
    bor
    -0.60
    POSITIVE LOGITS
     formation
    1.24
     formations
    1.07
    eering
    0.99
    idable
    0.98
     Formation
    0.95
     forming
    0.82
    formation
    0.79
    naire
    0.79
    aldehyde
    0.79
    regation
    0.75
    Activations Density 0.007%

    No Known Activations