INDEX

Explanations

instances and variations of the word "append" and its related forms

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

Revenir

-0.93

TagMode

-0.73

 isComment

-0.69

Referanser

-0.69

ⓧ

-0.68

BoxShadow

-0.67

kfree

-0.67

wpdb

-0.66

 HomeController

-0.66

Efq

-0.65

POSITIVE LOGITS

 Append

1.20

 append

1.09

 appended

1.08

Append

1.08

Appender

1.05

append

0.99

APPEND

0.97

 APPEND

0.90

appendTo

0.79

 追加

0.77

Activations Density 0.016%

instances and variations of the word "append" and its related forms

No Comments

No Known Activations