INDEX

Explanations

numeric representations or codes that pertain to specific regions or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

OGND

-1.00

 ſtand

-0.91

 faſt

-0.90

<bos>

-0.89

 myſelf

-0.88

 unſ

-0.88

 ſte

-0.87

 ſtre

-0.86

 ſta

-0.86

 juſ

-0.84

POSITIVE LOGITS

RenderAtEndOf

0.57

]")]

0.49

</b>

0.47

ffine

0.41

 SPDX

0.41

trina

0.41

tran

0.40

шем

0.39

ContentAsync

0.39

Đ

0.38

Activations Density 0.279%

numeric representations or codes that pertain to specific regions or categories

No Comments

No Known Activations