INDEX

Explanations

phrases related to ranges and measurements

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

"range" and its variations

np_acts-logits-general · gemini-2.0-flash

range or limit specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

Datuak

-0.76

ally

-0.61

︎

-0.57

awaiter

-0.56

iastes

-0.56

ènes

-0.54

 Thorne

-0.54

Aiheesta

-0.54

슷

-0.52

,:),

-0.52

POSITIVE LOGITS

 ranges

1.07

 Ranges

1.00

 Range

0.91

 range

0.88

ranges

0.88

Ranges

0.85

 RANGE

0.83

 gamut

0.75

Range

0.74

range

0.74

Activations Density 0.122%

phrases related to ranges and measurements

"range" and its variations

range or limit specifications

No Comments

No Known Activations