INDEX

Explanations

specific formatting or code-related references within the text

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

-0.58

-0.50

<bos>

-0.47

-0.45

her

-0.40

払

-0.39

 кем

-0.39

to

-0.39

-0.37

POSITIVE LOGITS

rungsseite

2.13

出版年

2.06

 autorytatywna

1.98

########.

1.91

 disambiguazione

1.89

 EconPapers

1.87

1.86

WithIOException

1.85

expandindo

1.85

:✨

1.84

Activations Density 0.160%

specific formatting or code-related references within the text

No Comments

No Known Activations