INDEX

Explanations

the word "fore" in various forms and contexts

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

The token "fore" or "Fore"

np_acts-logits-general · gemini-2.0-flash

fore +casted, arm, closure, head

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

isation

-0.59

ization

-0.59

lwjgl

-0.59

isations

-0.57

MigrationBuilder

-0.55

cemia

-0.55

keiten

-0.54

tonode

-0.54

verständlich

-0.54

 malheur

-0.53

POSITIVE LOGITS

 FORE

0.69

 Fore

0.68

 виправивши

0.66

 fore

0.60

Fore

0.59

tableFuture

0.53

fore

0.53

balleur

0.53

SequentialGroup

0.49

MOST

0.48

Activations Density 0.086%

the word "fore" in various forms and contexts

The token "fore" or "Fore"

fore +casted, arm, closure, head

No Comments

No Known Activations