INDEX

Explanations

ratings and scores related to products or content reviews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 CanadaChoose

-0.65

RTEE

-0.64

řeba

-0.64

Referencer

-0.63

antMatchers

-0.62

ftagPool

-0.61

()?;

-0.58

<()>

-0.57

 المعيارى

-0.57

]--;

-0.56

POSITIVE LOGITS

 rating

0.99

 ratings

0.77

rating

0.75

 Rating

0.74

 stars

0.73

 ✭✭

0.68

Rating

0.68

 RATING

0.67

RATING

0.66

ratings

0.64

Activations Density 0.180%

ratings and scores related to products or content reviews

No Comments

No Known Activations