INDEX

Explanations

terms related to floating-point data types and values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 تضيفلها

-0.73

 coraggio

-0.72

 Edelman

-0.71

 sbag

-0.69

 nemici

-0.68

 hornblende

-0.68

 وتسجيلات

-0.67

 vertu

-0.67

pan

-0.66

 modo

-0.66

POSITIVE LOGITS

 floats

1.69

 float

1.68

 FLOAT

1.67

 Float

1.65

 floated

1.49

Float

1.44

getFloat

1.37

float

1.33

FLOAT

1.33

Flo

1.26

Activations Density 0.090%

terms related to floating-point data types and values

No Comments

No Known Activations