INDEX

Explanations

references to existing systems, processes, or conditions

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

 énergé

-0.78

脚注の使い方

-0.73

 complètes

-0.73

AddTagHelper

-0.72

abestanden

-0.72

 שוליים

-0.64

 jdbcTemplate

-0.60

Hentet

-0.60

 juridiques

-0.60

 Himself

-0.60

POSITIVE LOGITS

 existing

1.43

existing

1.35

 Existing

1.32

Existing

1.30

 EXISTING

1.13

 existente

1.03

既存

0.95

 существу

0.94

 existentes

0.89

 bestaande

0.87

Activations Density 0.236%

references to existing systems, processes, or conditions

No Comments

No Known Activations