INDEX

Explanations

medical terminology and research-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 https

-1.14

https

-1.09

 impactful

-1.06

-1.05

 COVID

-0.94

-0.92

 onboarding

-0.85

 LGBTQ

-0.85

 microbiome

-0.84

nullptr

-0.83

POSITIVE LOGITS

 idéia

1.38

 daß

1.35

 Daß

1.30

 muß

1.19

 läßt

1.17

 mußte

1.15

faßt

1.11

 mußten

1.10

SourceChecksum

1.09

 Moslem

1.06

Activations Density 4.445%

medical terminology and research-related concepts

No Comments

No Known Activations