INDEX

Explanations

embedded code or technical specifications

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 betweenstory

-1.21

 насељу

-0.95

ⓧ

-0.94

 nakalista

-0.94

 Roskov

-0.93

 ویکی‌پدی

-0.92

хьтан

-0.91

Geplaatst

-0.91

 fieldNum

-0.90

oredCriteria

-0.88

POSITIVE LOGITS

0.58

0.54

0.53

0.50

mun

0.47

no

0.47

peti

0.45

لسط

0.45

Activations Density 0.083%

embedded code or technical specifications

No Comments

No Known Activations