© 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. 0-RES-JB
    11. 13762
    Prev
    Next
    INDEX
    Explanations

    words related to the process of creating or forming something

    oai_token-act-pair · gpt-3.5-turbo

    references 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 @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AppData
    -0.74
    utf
    -0.66
    amples
    -0.65
    dain
    -0.63
     Liv
    -0.63
    leep
    -0.63
    hol
    -0.62
     cared
    -0.62
    umbers
    -0.61
     apples
    -0.61
    POSITIVE LOGITS
     formation
    4.11
     Formation
    2.95
     formations
    2.58
     forming
    1.67
    formation
    1.59
     formed
    1.36
     dissolution
    1.34
     creation
    1.34
     emergence
    1.24
     composition
    1.20
    Activations Density 0.014%

    No Known Activations