INDEX

Explanations

keywords and variables related to programming and code structures

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

-0.71

-0.69

-0.66

‘

-0.59

“

-0.58

-0.57

↵↵

-0.56

the

-0.55

</strong>

-0.54

POSITIVE LOGITS

 متعلقه

1.18

expandindo

1.01

 Anſ

1.00

Билгалдахарш

0.99

iParam

0.97

ValueStyle

0.96

 Roskov

0.95

 disponibilités

0.93

 houſe

0.92

 ſever

0.92

Activations Density 0.119%

keywords and variables related to programming and code structures

No Comments

No Known Activations