INDEX

Explanations

references to user interactions or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 nakalista

-0.72

gettimeofday

-0.63

بوابة

-0.63

Portale

-0.63

UrlResolution

-0.59

Espèce

-0.58

NameInMap

-0.57

ircraft

-0.56

LOYEES

-0.55

voltaic

-0.54

POSITIVE LOGITS

 createState

0.70

BeginInit

0.64

BeginContext

0.63

 propOrder

0.60

ंदीखरीदारी

0.59

ⓧ

0.57



0.56

 réservés

0.53

IsContent

0.53

期刊论文

0.52

Activations Density 0.108%

references to user interactions or identifiers

No Comments

No Known Activations