INDEX

Explanations

references to medical or health-related guidelines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 houſe

-1.01

 виправивши

-1.00

 Houſe

-0.98

 Wikimedijinoj

-0.97

 يتيمه

-0.96

 חיצוניים

-0.94

#+#

-0.92

 pleaſure

-0.92

 itſelf

-0.92

 Мексичка

-0.91

POSITIVE LOGITS

↵

0.54

穂

0.34

数

0.34

…

0.34

先

0.33

es

0.33

 very

0.32

hal

0.32

Activations Density 2.884%

references to medical or health-related guidelines

No Comments

No Known Activations