INDEX

Explanations

references to medical professionals, particularly doctors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ListTile

-0.84

הערות

-0.72

 Bunt

-0.69

 étoient

-0.69

gunas

-0.68

bleib

-0.67

 Limburg

-0.67

undes

-0.66

 Guth

-0.66

 Oblivion

-0.66

POSITIVE LOGITS

 Drury

1.30

Dr

1.25

Dr

1.18

 doctor

0.96

DR

0.95

dr

0.93

dr

0.93

doc

0.92

Drs

0.91

 DOCTOR

0.87

Activations Density 0.048%

references to medical professionals, particularly doctors

No Comments

No Known Activations