INDEX

Explanations

names of places and geographic features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

edly

-0.66

itoba

-0.63

 onResponse

-0.63

 Tirol

-0.61

 VEGAS

-0.61

 Yunnan

-0.60

 ANGELES

-0.60

enderror

-0.59

 SYDNEY

-0.58

 Sarawak

-0.57

POSITIVE LOGITS

mybatisplus

0.71

ValueStyle

0.65

BagConstraints

0.59

 Quelles

0.58

 North

0.53

GHIJKLM

0.51

 South

0.51

 Upper

0.51

multicolumn

0.49

ärzt

0.49

Activations Density 2.062%

names of places and geographic features

No Comments

No Known Activations