INDEX

Explanations

markers indicating structural formatting or special coding elements

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

dem

-0.51

聽

-0.49

 lâu

-0.49

isie

-0.49

schod

-0.48

naut

-0.47

ersch

-0.47

liſh

-0.47

افظة

-0.46

ровок

-0.46

POSITIVE LOGITS

########.

0.84

EndGlobalSection

0.71

BufferException

0.69

 iprot

0.66

Zeneca

0.66

ergies

0.65

sizeCache

0.65

Rujuakan

0.64

 Feynman

0.63

contentLoaded

0.62

Activations Density 0.126%

markers indicating structural formatting or special coding elements

No Comments

No Known Activations