INDEX

Explanations

ratings and reviews within the context of evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

()?;

-0.59

 يتيمه

-0.58

 CanadaChoose

-0.56

<()>

-0.55

 المعيارى

-0.55

antMatchers

-0.54

OGND

-0.52

scryfall

-0.52

 iprot

-0.51

RTEE

-0.51

POSITIVE LOGITS

 rating

0.88

 ratings

0.69

 stars

0.68

RATING

0.67

rating

0.65

 ✭✭

0.63

 Rating

0.63

 graded

0.63

★★★★☆

0.61

 score

0.61

Activations Density 0.165%

ratings and reviews within the context of evaluations

No Comments

No Known Activations