INDEX

Explanations

phrases that indicate references or attributions 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 @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

astify

-0.65

ьаж

-0.63

TagHelpers

-0.61

 ogóle

-0.59

StructEnd

-0.53

 firebaseConfig

-0.52

 Савезне

-0.51

AxisAlignment

-0.51

 dàng

-0.50

ysacchar

-0.50

POSITIVE LOGITS

Secondo

0.68

μφωνα

0.67

according

0.67

 ACCORD

0.63

According

0.62

 according

0.61

 Secondo

0.61

 According

0.60

Selon

0.55

 accordance

0.53

Activations Density 0.122%

phrases that indicate references or attributions in the text

No Comments

No Known Activations