INDEX

Explanations

references to political figures and associated terms

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

 myſelf

-0.70

 faſt

-0.69

Kilder

-0.64

 ſeveral

-0.63

 purpoſe

-0.62

 whoſe

-0.60

uſ

-0.59

 houſe

-0.59

 fubject

-0.58

 themſelves

-0.58

POSITIVE LOGITS

Obrázky

0.69

rungsseite

0.63

 saites

0.61

ItemBackground

0.59

rad

0.57

بوابة

0.57

OCCURRED

0.56

hower

0.55

Svg

0.55

Amb

0.54

Activations Density 2.930%

references to political figures and associated terms

No Comments

No Known Activations