© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 4938
    Prev
    Next
    INDEX
    Explanations

    terms related to growth, expansion, or increase

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "expanding" and related improvement concepts

    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
     stood
    -0.69
     belonged
    -0.68
     took
    -0.67
    ueller
    -0.64
     proceeded
    -0.63
    ilege
    -0.63
    sat
    -0.63
    FU
    -0.63
     reside
    -0.63
     stand
    -0.63
    POSITIVE LOGITS
     expanding
    2.47
     improving
    2.30
     evolving
    2.00
     accelerating
    1.98
     widening
    1.94
     advancing
    1.88
     increasing
    1.87
     shrinking
    1.86
     exploding
    1.78
     deepening
    1.76
    Activations Density 0.046%

    No Known Activations