INDEX

Explanations

geographical terms related to specific locations and natural features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 equivalente

-0.44

Doubt

-0.43

yip

-0.43

 thermique

-0.42

hintText

-0.42

zip

-0.42

 rooms

-0.42

ever

-0.41

入る

-0.41

 clásicos

-0.41

POSITIVE LOGITS

GEBURTSDATUM

0.93

 waarop

0.92

 surface

0.91

 Surfaces

0.84

mybatisplus

0.82

 للاسماء

0.81

 Surface

0.80

surface

0.80

 SURFACE

0.78

surfaces

0.77

Activations Density 0.693%

geographical terms related to specific locations and natural features

No Comments

No Known Activations