INDEX

Explanations

mentions of database connection-related terms

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

Geplaatst

-0.84

 Tade

-0.77

++++++++++++++++

-0.75

 plais

-0.72

 PARTIC

-0.67

 Kome

-0.67

 Neub

-0.65

FERENCE

-0.64

––––

-0.64

 Elas

-0.63

POSITIVE LOGITS

 conn

1.59

conn

1.50

 Conn

1.47

 Connors

1.45

Conn

1.25

 Connor

1.19

Connor

1.17

CONN

0.98

IsPostBack

0.82

CON

0.81

Activations Density 0.006%

mentions of database connection-related terms

No Comments

No Known Activations