INDEX

Explanations

expressions indicating a comparison or contrast in contexts related to evaluation or analysis

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

 للمعارف

-0.58

outez

-0.54

ranges

-0.51

 répondit

-0.50

consulté

-0.50

 nacionais

-0.50

COC

-0.49

istoitu

-0.47

 跳转至

-0.47

 répondu

-0.46

POSITIVE LOGITS

 المعيارى

0.80

webElementXpaths

0.75

expandindo

0.72

oneofs

0.67

 AssemblyCulture

0.66

曖昧さ回避

0.63

rungsseite

0.56

PyExc

0.56

ãng

0.54

 actually

0.54

Activations Density 0.378%

expressions indicating a comparison or contrast in contexts related to evaluation or analysis

No Comments

No Known Activations