INDEX

Explanations

specific terminology related to medical or scientific concepts and conditions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sanitaria

-0.80

 ilustracji

-0.78

 Heft

-0.77

-0.73

ร้อน

-0.70

 Fonda

-0.70

-0.69

варь

-0.69

Weil

-0.69

 kultury

-0.68

POSITIVE LOGITS

ſelves

1.32

ſem

1.28

ſelf

1.19

ghijklmnop

1.18

.}~\

1.14

 Anſ

1.13

ſtre

1.11

IBLIO

1.11

iſter

1.10

geſ

1.10

Activations Density 3.021%

specific terminology related to medical or scientific concepts and conditions

No Comments

No Known Activations