INDEX

Explanations

locations and geographical features

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<eos>

-0.50

 including

-0.48

失

-0.45

andre

-0.45

那些

-0.44

зь

-0.44

for

-0.43

↵↵

-0.43

芝

-0.43

et

-0.43

POSITIVE LOGITS

$_"

0.90

 nestled

0.87

webElementGuid

0.83

 itſelf

0.82

 Monfieur

0.81

 perched

0.80

CodedInputStream

0.80

 ―――――

0.79

 iſt

0.79

 tucked

0.78

Activations Density 0.192%

locations and geographical features

No Comments

No Known Activations