INDEX

Explanations

the word "direct" and its variations in various contexts

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

"direct" preceding another word

np_acts-logits-general · gemini-2.0-flash

direct followed by noun

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ModelExpression

-0.84

InjectAttribute

-0.74

unmodifiable

-0.73

ResumeLayout

-0.71

endpush

-0.70

 MotionEvent

-0.70

 AssemblyCompany

-0.69

 createSlice

-0.66

setVerticalGroup

-0.65

JNIEnv

-0.64

POSITIVE LOGITS

Direct

1.30

 direct

1.25

 DIRECT

1.25

 Direct

1.22

DIRECT

1.20

direct

1.20

 Directly

1.10

 directly

1.00

directly

1.00

 directo

0.94

Activations Density 0.096%

the word "direct" and its variations in various contexts

"direct" preceding another word

direct followed by noun

No Comments

No Known Activations