INDEX

Explanations

phrases that express the notion of having experienced or undergone events or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 isoliert

-0.73

 pylint

-0.72

cepatan

-0.69

имущества

-0.68

 Hyman

-0.67

odotus

-0.66

SourceChecksum

-0.66

 paramString

-0.65

כונה

-0.65

 Sioux

-0.65

POSITIVE LOGITS

have

0.88

ReusableCell

0.83

HAV

0.79

DrawerToggle

0.76

曖昧さ回避

0.75

had

0.73

 have

0.72

had

0.72

HAVE

0.72

Have

0.71

Activations Density 0.118%

phrases that express the notion of having experienced or undergone events or conditions

No Comments

No Known Activations