INDEX

Explanations

occurrences of numbers or numerical references in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.70

-0.61

-0.57

..

-0.52

.....

-0.51

↵↵↵

-0.50

-0.49

…..

-0.48

______

-0.47

POSITIVE LOGITS

 ſta

0.87

 iſt

0.87

 raiſ

0.80

 myſelf

0.79

 ſche

0.79

 يتيمه

0.79

 ſever

0.78

ſy

0.77

 ſch

0.77

InputBorder

0.77

Activations Density 0.424%

occurrences of numbers or numerical references in the text

No Comments

No Known Activations