INDEX

Explanations

significant occurrences of numbers and structured data references

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 milliers

-0.77

 centaines

-0.76

everywhere

-0.72

 variés

-0.71

们

-0.70

 everywhere

-0.69

InitVars

-0.69

itária

-0.69

 berbagai

-0.67

 numerosi

-0.66

POSITIVE LOGITS

 namely

0.77

 apiece

0.76

分别是

0.73

分別

0.71

 respectively

0.70

respectively

0.69

分别

0.66

namely

0.63

 iaitu

0.62

 each

0.61

Activations Density 0.628%

significant occurrences of numbers and structured data references

No Comments

No Known Activations