INDEX

Explanations

phrases indicating ease of use and accessibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

ніципа

-0.77

TagMode

-0.61

 propOrder

-0.60

tagHelperRunner

-0.59

Jeografia

-0.59

 respectively

-0.59

 externi

-0.56

 соответственно

-0.55

TypedDataSet

-0.54

 berjudul

-0.54

POSITIVE LOGITS

 easy

0.89

 easily

0.87

 Easily

0.80

easy

0.79

easily

0.78

easier

0.77

Easily

0.77

 Easier

0.75

 mudah

0.74

 easier

0.73

Activations Density 0.135%

phrases indicating ease of use and accessibility

No Comments

No Known Activations