INDEX

Explanations

negative numbers and their contexts related to significant events or issues

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

########.

-0.72

SharedCtor

-0.67

aarrggbb

-0.57

ANNES

-0.52

 leopardo

-0.51

 muualla

-0.50

;#

-0.50

 calendriers

-0.48

تال

-0.48

ccione

-0.48

POSITIVE LOGITS

 Chwiliwch

0.63

 становника

0.61

 Apare

0.60

 Wissenschaften

0.58

SuppressMessage

0.58

atimes

0.58

Jez

0.57

 tfsi

0.57

 thistle

0.56

WebVitals

0.56

Activations Density 0.248%

negative numbers and their contexts related to significant events or issues

No Comments

No Known Activations