© 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. 6479
    Prev
    Next
    INDEX
    Explanations

    verbs related to growth or expansion

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of growth or increase, particularly when discussing expansion in various contexts

    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
    ariat
    -0.68
     Jud
    -0.67
     Derby
    -0.67
    tale
    -0.65
    eree
    -0.65
    rie
    -0.65
     Zeit
    -0.65
    alia
    -0.65
     Diet
    -0.65
    jury
    -0.64
    POSITIVE LOGITS
     expand
    3.39
     Expand
    2.47
     expands
    2.21
     expanding
    2.10
     expanded
    2.05
     expansion
    2.05
     expansions
    1.90
     enlarge
    1.77
     broaden
    1.72
     widen
    1.65
    Activations Density 0.010%

    No Known Activations