INDEX

Explanations

phrases related to technical usage and configurations, particularly in computing and server contexts

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

preceding "want," "need," or similar words

np_acts-logits-general · gemini-2.0-flash

who need/want

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

Ligações

-0.47

bootstrapcdn

-0.46

спол

-0.46

peritoneal

-0.45

 HasFactory

-0.44

ary

-0.43

isInitialized

-0.43

 brooms

-0.43

лық

-0.42

σιο

-0.42

POSITIVE LOGITS

 need

1.01

 needs

0.99

 needing

0.95

needs

0.91

需要

0.86

 Needs

0.86

 Need

0.85

need

0.84

 NEED

0.84

Need

0.82

Activations Density 0.711%

phrases related to technical usage and configurations, particularly in computing and server contexts

preceding "want," "need," or similar words

who need/want

No Comments

No Known Activations