INDEX

Explanations

the occurrence of the word "shut" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

yntaxException

-0.95

SharedDtor

-0.91

 autorytatywna

-0.83

 ligiloj

-0.82

rungsseite

-0.81

脚注の使い方

-0.80

Биография

-0.79

brainly

-0.79

mybatisplus

-0.78

 Мексичка

-0.77

POSITIVE LOGITS

 activation

0.91

paper

0.84

 shut

0.83

 Activation

0.79

 paper

0.75

 activating

0.75

Paper

0.74

 activates

0.73

 activate

0.72

 activated

0.70

Activations Density 0.110%

the occurrence of the word "shut" in various contexts

No Comments

No Known Activations