INDEX

Explanations

references to bees and bee-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 للمعارف

-0.90

 '\\;'

-0.73

gdx

-0.72

 насељу

-0.67

 carats

-0.67

 مرئيه

-0.66

 Paleozoic

-0.66

 везе

-0.66

 layui

-0.65

atrième

-0.63

POSITIVE LOGITS

 Frontier

0.73

 mosquito

0.72

Bee

0.71

 Ordinance

0.71

 ordinance

0.70

 blast

0.67

Bee

0.66

 infer

0.65

Din

0.65

 Infer

0.65

Activations Density 0.348%

references to bees and bee-related terminology

No Comments

No Known Activations