INDEX

Explanations

references to quantities and measurements

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

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

Portale

-0.94

Vidite

-0.85

 للمعارف

-0.85

 Meksiku

-0.82

expandindo

-0.81

</tfoot>

-0.80

 EconPapers

-0.78

 وتسجيلات

-0.77

Jereo

-0.76

Autoritní

-0.75

POSITIVE LOGITS

 halfway

0.72

 midway

0.68

 half

0.64

 five

0.62

 eight

0.60

 four

0.58

 three

0.58

six

0.57

 seven

0.54

 twice

0.53

Activations Density 0.226%

references to quantities and measurements

No Comments

No Known Activations