© 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. 1-RES-JB
    11. 3458
    Prev
    Next
    INDEX
    Explanations

    terms related to the formation of groups, organizations, or structures

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "formation."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verse
    -0.70
    enny
    -0.67
    cedented
    -0.65
    bor
    -0.64
     living
    -0.63
    ience
    -0.63
    hou
    -0.63
    istors
    -0.62
    ient
    -0.62
    verning
    -0.62
    POSITIVE LOGITS
     formation
    1.47
     formations
    1.25
     Formation
    1.15
    eering
    0.92
    idable
    0.86
     forming
    0.86
    formation
    0.85
     Awareness
    0.78
    naire
    0.76
    aldehyde
    0.72
    Activations Density 0.007%

    No Known Activations