INDEX

Explanations

parameters and fields in data structures or configurations

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

code, and data types/values

np_acts-logits-general · gemini-2.0-flash

programming language keywords

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ویکی‌پدی

-0.91

parsedMessage

-0.89

Tembelea

-0.82

tvguidetime

-0.81

 propOrder

-0.80

 betweenstory

-0.80

 متعلقه

-0.77

 OMITBAD

-0.77

AndEndTag

-0.74

WriteBarrier

-0.73

POSITIVE LOGITS

0.49

0.48

↵↵

0.40

).

0.40

↵

0.39

ful

0.36

);

0.36

，

0.36

。

0.33

Activations Density 0.138%

parameters and fields in data structures or configurations

code, and data types/values

programming language keywords

No Comments

No Known Activations