INDEX

Explanations

quality and clarity in written communication

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

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

日閲覧

-0.60

 MotionEvent

-0.57

urbed

-0.55

---*/

-0.55

djangoproject

-0.54

UNIDENTIFIED

-0.52

typeorm

-0.52

sendMail

-0.52

Portail

-0.51

Portály

-0.51

POSITIVE LOGITS

 concise

1.54

 succinct

1.33

 brevity

1.23

 brief

1.07

 succinctly

1.05

 Concise

1.04

 condensed

0.91

 short

0.89

 terse

0.88

 shorter

0.88

Activations Density 0.489%

quality and clarity in written communication

No Comments

No Known Activations