INDEX

Explanations

code related to database entity definitions and relationships

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

Relational database context

np_acts-logits-general · gemini-2.0-flash

entities and code structures

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Offisielt

-0.67

guenos

-0.63

 Grecs

-0.61

 financières

-0.61

 informée

-0.60

 eorum

-0.59

%)$

-0.59

GraphicsUnit

-0.59

ього

-0.58

 contemporaine

-0.58

POSITIVE LOGITS

 employee

0.82

 users

0.73

 user

0.73

 student

0.72

 Users

0.72

 posts

0.70

 User

0.70

job

0.68

 customer

0.67

 product

0.67

Activations Density 0.553%

code related to database entity definitions and relationships

Relational database context

entities and code structures

No Comments

No Known Activations