INDEX

Explanations

instances of special characters and formatting tokens in the text

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

 samar

-0.65

lesssim

-0.64

ne

-0.63

bra

-0.63

 model

-0.62

ser

-0.62

elry

-0.62

 front

-0.61

ang

-0.61

 Levin

-0.60

POSITIVE LOGITS

 varandra

0.88

enumi

0.85

 bakgrund

0.84

antaranya

0.81

 consultato

0.78

 maș

0.78

 myö

0.76

 häls

0.74

 térmico

0.74

 vulga

0.73

Activations Density 0.062%

instances of special characters and formatting tokens in the text

No Comments

No Known Activations