INDEX

Explanations

programming constructs related to assigning and using variables

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

ंदीखरीदारी

-1.06

 disambiguazione

-1.06

 مرئيه

-0.93

WebVitals

-0.93

 Roskov

-0.92

Билгалдахарш

-0.90

ReusableCell

-0.88

 ujednoznacz

-0.88

NameInMap

-0.86

MigrationBuilder

-0.82

POSITIVE LOGITS

{$\

0.49

$\

0.49

rons

0.43

$\

0.42

her

0.41

kana

0.40

bind

0.40

 Chase

0.39

ron

0.39

Activations Density 0.152%

programming constructs related to assigning and using variables

No Comments

No Known Activations