INDEX

Explanations

terms related to medical research and clinical studies on treatments and their effectiveness

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

хьтан

-0.74

 pleaſure

-0.73

 purpoſe

-0.72

 Monfieur

-0.72

Autoritní

-0.69

Efq

-0.68

 myſelf

-0.68

 autorytatywna

-0.67

 auffi

-0.66

 ſtate

-0.65

POSITIVE LOGITS

 investigated

1.05

 studied

1.03

 discussed

0.98

 explored

0.95

 subject

0.90

 examined

0.88

 analyzed

0.87

 debated

0.86

studied

0.80

 topic

0.78

Activations Density 0.768%

terms related to medical research and clinical studies on treatments and their effectiveness

No Comments

No Known Activations