INDEX

Explanations

terms related to interpretation and analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

isOk

-0.71

 stava

-0.67

Rik

-0.65

Rik

-0.65

ensatz

-0.65

haden

-0.64

 adelante

-0.64

Fin

-0.64

Cross

-0.64

CardModule

-0.64

POSITIVE LOGITS

Mapper

1.54

 Mapper

1.36

 mapper

1.31

ibatis

1.28

mapper

1.24

 worship

0.94

Worship

0.93

worship

0.91

exploitation

0.86

 AutoMapper

0.85

Activations Density 0.088%

terms related to interpretation and analysis

No Comments

No Known Activations