INDEX

Explanations

user-generated content and feedback, particularly in the context of reviews and experiences related to products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Willkommen

-0.67

archiviato

-0.67

UrlResolution

-0.64

]--;

-0.64

{}/

-0.62

dhism

-0.60

 AssemblyProduct

-0.59

 Baillargeon

-0.58

Herzlich

-0.57

tagext

-0.57

POSITIVE LOGITS

Verified

0.68

 Verified

0.64

verified

0.63

 excellent

0.61

 Reviewed

0.61

 Anonymous

0.60



0.60

 answered

0.58

 Excellent

0.58

Excellent

0.57

Activations Density 0.076%

user-generated content and feedback, particularly in the context of reviews and experiences related to products or services

No Comments

No Known Activations