INDEX

Explanations

phrases related to procedural or technical descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

tagHelperRunner

-0.85

+#+#

-0.78

:✨

-0.76

 SwitchCompat

-0.75

tanleria

-0.74

RTEE

-0.73

AndEndTag

-0.72

 onOptions

-0.71

ActionCreators

-0.70

lasty

-0.67

POSITIVE LOGITS

原始内容存档于

0.48

 finally

0.43

Finally

0.41

Loco

0.41

0.38

 Loco

0.38

 yürü

0.37

人工

0.36

 walk

0.36

awakeFromNib

0.36

Activations Density 3.750%

phrases related to procedural or technical descriptions

No Comments

No Known Activations