INDEX

Explanations

phrases related to statistical summaries or totals in data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

----</

-0.73

İstinadlar

-0.70

 pleaſure

-0.69

'>";

-0.69

%");

-0.65

%";

-0.63

 للمعارف

-0.62

oredCriteria

-0.62

 Typical

-0.61

)}</

-0.60

POSITIVE LOGITS

нительно

0.73

 totalt

0.68

 sebanyak

0.67

 insgesamt

0.66

 câte

0.62

 totaal

0.61

計

0.61

 resultCode

0.60

 exactement

0.60

一共

0.58

Activations Density 0.180%

phrases related to statistical summaries or totals in data

No Comments

No Known Activations