INDEX

Explanations

conjunctions and phrases indicating conditionality or relationship between elements in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

sizeCache

-0.63

이나

-0.62

 maupun

-0.61

 pergunta

-0.60

 OTHERS

-0.59

 Վերցված

-0.58

StoryboardSegue

-0.57

 inquest

-0.56

 그의

-0.56

 tokenize

-0.56

POSITIVE LOGITS

 plenty

0.93

 lots

0.89

0.82

an

0.78

 high

0.74

 excellent

0.71

 great

0.70

 strong

0.69

 incredible

0.64

plenty

0.63

Activations Density 0.285%

conjunctions and phrases indicating conditionality or relationship between elements in a text

No Comments

No Known Activations