INDEX

Explanations

references to personal names within text

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

例句

-0.74

期刊论文

-0.62

 Vaticano

-0.59

riever

-0.59

 abbot

-0.57

 betreft

-0.56

 Radu

-0.56

ież

-0.56

最快更新

-0.54

Predecesor

-0.54

POSITIVE LOGITS

 names

2.10

 name

2.06

 Names

1.80

 Name

1.73

 NAME

1.64

 NAMES

1.52

names

1.52

 Namen

1.43

Name

1.40

Names

1.40

Activations Density 0.092%

references to personal names within text

No Comments

No Known Activations