INDEX

Explanations

references to the United States

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Rüyada

-0.81

 corret

-0.79

 bezeichneter

-0.77

Advertisements

-0.75

\}}

-0.74

windowFixed

-0.72

 memer

-0.71

 Moreira

-0.71

"]));

-0.70

oredCriteria

-0.67

POSITIVE LOGITS

0.85

0.74

rea

0.69

 féd

0.63

एस

0.63

InputBorder

0.62

jména

0.62

 Schülern

0.61

 trebui

0.60

sS

0.59

Activations Density 0.047%

references to the United States

No Comments

No Known Activations