INDEX

Explanations

summaries or outlines of content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 Math

-0.63

 acido

-0.61

fires

-0.59

ջ

-0.56

yat

-0.56

djangoproject

-0.54

na

-0.54

杯

-0.53

endphp

-0.53

POSITIVE LOGITS

 summaries

1.34

 summary

1.26

 Summaries

1.15

maries

1.13

Recap

1.11

 summar

1.11

summary

1.10

 overview

1.10

 myſelf

1.09

 themſelves

1.09

Activations Density 0.107%

summaries or outlines of content

No Comments

No Known Activations