INDEX

Explanations

references to specific weeks or periods, indicating a temporal focus 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 @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

DataMember

-0.64

omány

-0.58

 nahilalakip

-0.56

 lagging

-0.55

 Strö

-0.55

 thither

-0.54

 sottile

-0.54

 occafion

-0.54

 Excellency

-0.54

NamedQuery

-0.53

POSITIVE LOGITS

 weekend

0.93

 Week

0.88

 WEEK

0.82

Week

0.81

 Weekend

0.80

weekend

0.78

 WEEKEND

0.75

 week

0.73

 censiti

0.71

WEEK

0.69

Activations Density 0.100%

references to specific weeks or periods, indicating a temporal focus in the text

No Comments

No Known Activations