INDEX

Explanations

statements made by individuals expressing their opinions or experiences

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

 BorderRadius

-0.49

########.

-0.48

 Dân

-0.47

のでしょう

-0.47

 reportedly

-0.46

のかも

-0.45

lite

-0.45

のですね

-0.45

 supposedly

-0.43

 enda

-0.42

POSITIVE LOGITS

 said

1.69

said

1.18

Said

1.01

 SAID

0.95

 Said

0.93

 faid

0.91

 laughed

0.89

 dijo

0.86

 gesagt

0.84

 joked

0.82

Activations Density 0.164%

statements made by individuals expressing their opinions or experiences

No Comments

No Known Activations