INDEX

Explanations

references to "kid" and "boss" 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 @ 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

 bezeichneter

-0.78

 nakalista

-0.77

 tartalomajánló

-0.76

énario

-0.75

 disambiguazione

-0.75

ImageContext

-0.73

 مرئيه

-0.71

xase

-0.67

+#+#

-0.67

Ill

-0.66

POSITIVE LOGITS

 Triple

0.91

 triple

0.84

Triple

0.81

triple

0.76

icoot

0.63

Kid

0.59

 TextAppearance

0.58

клопе

0.58

Les

0.57

Kid

0.57

Activations Density 0.026%

references to "kid" and "boss" in various contexts

No Comments

No Known Activations